PhD Learning to Leverage Complex Morphologies Data-Driven Modeling and Intelligent Control for Unconventional Robots

Details

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

Unconventional robotic systems—such as soft robots, shape-morphing structures, bio-inspired mechanisms, and robots with distributed or compliant materials—exhibit complex, high-dimensional dynamics that are poorly captured by traditional rigid-body models. Their behaviour emerges from tight coupling between morphology, materials, and control, leading to nonlinear, partially observable dynamics that challenge classical modeling and control methods. This PhD project aims to develop AI-enhanced modeling and control frameworks that integrate data-driven learning with physics-based structure, enabling robots to exploit their morphology as a source of mechanical intelligence rather than a limitation.

The project will focus first on learning expressive yet physically grounded models of complex robotic morphologies. Surrogate dynamic models will be developed using neural ordinary differential equations, graph neural networks for distributed compliant structures, and differentiable physics simulators. Physics-informed learning will be used to embed known mechanical constraints—such as elasticity, incompressibility, and actuation or tendon-routing constraints—into the learning process, improving model fidelity, stability, and generalization.

Building on these models, the project will design hybrid physics–machine learning control strategies for nontraditional robots. Model-based nonlinear control techniques, including energy shaping and model predictive control, will be augmented with learned components that compensate for unmodeled dynamics and uncertainty. Emphasis will be placed on adaptive and online learning approaches, allowing controllers to update continuously in response to environmental changes, material variability, or damage.

The project will further investigate AI-driven exploration and autonomous skill discovery using reinforcement learning and unsupervised methods to identify effective locomotion and manipulation behaviours in robots with unconventional bodies. Control policies and learning architectures will be explicitly morphology-aware, reflecting the robot’s physical graph, material distribution, or actuation layout.

Robustness and generalization across tasks, environments, and morphologies will be addressed using domain randomization, meta-learning, and transfer learning. All methods will be validated on physical robotic platforms, such as soft continuum manipulators, pneumatic or tendon-driven systems, bio-inspired crawlers, and tensegrity robots, with evaluation focused on performance, adaptability, and resilience in unstructured and uncertain conditions.

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in degree in Electrical / Control / Mechanical / Mechatronics / Control Engineering, Applied Physics / Applied Mathematics (with demonstrable training / experience in nonlinear dynamics / nonlinear differential equations, Computing Science (with demonstrable training / experience in AI / ML / ANN coding)

Application Procedure:

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 lead 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.

Informal enquiries can be made by contacting Professor S Aphale at s.aphale@abdn.ac.uk. 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 researchadmissions@abdn.ac.uk