Physics-Informed Neural Networks for control of compliant robotic systems

We are seeking a highly motivated PhD candidate to join our interdisciplinary Artificial intelligence, Robotics and Mechatronic Systems Group (ARMS), to advance the modelling and control of complex, compliant robotic systems using Physics-Informed Neural Networks (PINNs). This research aims to address critical challenges in the control of unconventional robots, such as so: and origami robots, that require innovative control techniques to manage their complex dynamics, nonlinear behaviours, and interactions with changing environments.

The focus of this work is the development of robust, safe, and resilient control methodologies for compliant robotic systems. Specifically, this research will apply and extend PINNs for modelling and controlling these robots under conditions where external perturbations (e.g., unpredictable environmental interactions, variable loads, and force disturbances) may impact performance.

The candidate will work on combining PINN-based learned models with traditional model-based controllers, often developed from first principles, to achieve precise, adaptable, and resilient performance in complex robotic systems. By merging established and novel control methods, the project aims to ensure both theoretical stability and practical robustness for compliant robots that are safe to interact with people and adaptable to environmental changes. This research will advance both the theoretical and practical aspects of control in compliant robotics, resulting in breakthrough methodologies for creating resilient, safe, and adaptable robots. This project offers an exciting opportunity to make impactful contributions in the fields of robotics, machine learning, and control engineering.

CANDIDATE BACKGROUND:

Applicants should hold a First-Class UK Bachelor’s or Master’s Degree (preferred) or equivalent, in Robotics, Mechanical Engineering, Computer Science, Electrical Engineering, Physics, Applied Mathematics or a related field.

· Prior experience in working with mathematical models of dynamical systems or neural network architectures is highly desirable, as is familiarity with partial differential equations (PDEs) and their numerical solution methods.

·Proficiency in at least one programming language / software package commonly used for scientific computing (MATLAB / Python / C).

·Solid understanding in control theory and its application to robotics.

The successful candidate will:

· be part of an inspiring multidisciplinary, international, and academic environment. The university offers a dynamic ecosystem with enthusiastic colleagues in which internationalization is an important part of the strategic agenda.

· A professional and personal development program within University of Aberdeen.

· Receive excellent support for research and facilities for professional and personal development.

·Excellent working conditions, an exciting scientific environment, and a green and lively campus.

We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

• Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php
• You should apply for PhD in Engineering to ensure your application is passed to the correct team for processing.
• Please clearly note the name of the supervisor and project title on the application form. If you do not include these details, it may not be considered for the studentship.
• Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.
• Please note: you do not need to provide a research proposal with this application
• If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at [[Email Address Removed]]. Project specific enquiries should be directed to Dr S Aphale ([Email Address Removed]).

The start date of the project is to be agreed with the lead supervisor but should be as soon as practically possible.

Please note, your application may be shared with any external funders of this PhD Studentship, and any external members of the supervisory team