Reinforcement Learning for Autonomous (De)(Re)Manufacturing of High-Value Products (Ref: SF-JO-2026/2)

About the Project

The ‘what’

This PhD will develop reinforcement learning (RL) methods to enable robots to autonomously disassemble, repair, and remanufacture high-value products such as aerospace components, automotive systems, and electronics.

The ‘why’

High-value products are often discarded or underutilised at end-of-life due to the complexity and cost of disassembly and remanufacturing. These processes are typically manual, requiring skilled operators to deal with variability, uncertainty, and incomplete information (e.g. unknown wear, hidden fasteners, or damage).

Advancing autonomous (de)(re)manufacturing is critical for enabling a circular economy, reducing waste, and lowering carbon emissions. Reinforcement learning offers a promising route to equip robots with the ability to learn adaptive strategies for complex, sequential tasks under uncertainty. This project addresses a key challenge: how to make RL robust, safe, and data-efficient enough for real-world remanufacturing applications.

The ‘who’

You will be based at Loughborough University, working within a multidisciplinary team spanning robotics, artificial intelligence, and advanced manufacturing. Supervision will include experts in reinforcement learning, robotic manipulation, and sustainable manufacturing, with collaboration opportunities across UK research partners.

Industry engagement and sponsorship

The project will engage with industrial stakeholders in aerospace, automotive, and remanufacturing sectors, providing real-world components, use cases, and validation scenarios. Opportunities for industrial placements or secondments will be available, ensuring strong alignment with industry needs.

Aims and objectives

• Develop reinforcement learning algorithms for sequential disassembly and remanufacturing tasks
• Enable adaptive decision-making under uncertainty (e.g. unknown product condition)
• Integrate perception and manipulation for identifying and interacting with components
• Ensure safe and reliable execution in real-world robotic systems

Methodology

The project will combine AI, robotics, and experimental validation:

• Formulate disassembly and remanufacturing as sequential decision-making problems
• Develop model-free and model-based RL approaches, including hierarchical and offline RL
• Use simulation environments and digital twins to accelerate learning
• Explore sim-to-real transfer and safety-constrained learning
• Validate on robotic platforms performing tasks such as fastener removal, component sorting, and repair operations

Skills and development

You will gain expertise in:

• Reinforcement learning and AI for decision-making
• Robotic manipulation and perception
• Simulation and digital twin technologies
• Sustainable and circular manufacturing systems

You will also develop transferable skills in interdisciplinary research, critical thinking, and collaboration with industry.

Career pathways

This PhD prepares you for careers in:

• AI and robotics for sustainable manufacturing
• Advanced manufacturing and remanufacturing industries
• Research and development in autonomous systems
• Academic careers in AI, robotics, or circular economy technologies

Why Loughborough

Loughborough University provides a world-leading environment in manufacturing, robotics, and sustainability research. You will benefit from:

• Access to cutting-edge robotic and manufacturing facilities
• A strong interdisciplinary and impact-driven research culture
• Structured doctoral training and career development support
• Close links with industry and innovation programmes

Name of primary supervisor/CDT lead: John Oyekan (j.o.oyekan@lboro.ac.uk)

Entry requirements:

Applicants should have:

• A first-class or 2:1 degree in Robotics, Computer Science, AI, Mechanical/Electrical Engineering, or a related discipline
• Strong programming skills (e.g. Python, C++)
• Solid foundation in mathematics (probability, optimisation, linear algebra)

Desirable:

• Experience with reinforcement learning or machine learning
• Familiarity with robotics, control, or perception systems
• Interest in sustainability, circular economy, or manufacturing

English language requirements: Applicants must meet the minimum English language requirements. Further details are available on the International website.

Bench fees required: No

Closing date of advert: 31 October 2026

Start date: 01 February 2027

Full-time/part-time availability: Full-time 3 years

Fee band: 2026/27 Band RB (UK £5,238, International £29,500)

How to Apply:

All applications should be made online. Under Campus, please select Loughborough and select Programme "Electronic, Electrical and Systems Engineering’. Please quote the advertised reference number ‘SF-JO-2026/2’ under the finance section in your application.

Applications must include a personal statement, up-to-date curriculum vitae (CV), details of two referees (one from your highest degree qualification), certified certificates and transcripts for all completed degree programmes, and a reference to the project ‘SF-JO-2026/2’.

Submission of a research proposal is not essential but may strengthen your application. To avoid delays in processing your application, please ensure that you submit the minimum supporting documents above.

Project search terms: artificial intelligence, computer science - other, control systems, human computer interaction, manufacturing engineering, robotics

Email address Wolfson: ws.phdadmin@lboro.ac.uk