Machine Learning in Dynamical Systems for Sensor Signal Processing University of Edinburgh in United Kingdom

This PhD opportunity at the University of Edinburgh’s School of Engineering focuses on advancing machine learning methods for dynamical systems in sensor signal processing. Dynamical system models are foundational in control, signal processing, and sensor fusion, enabling applications such as multi-object detection and tracking, robotic SLAM, and calibration of autonomous networked sensors. Traditional approaches combine known physics with stochastic modeling, but recent advances in machine learning allow for significant performance improvements by leveraging data and model complexity.

The project aims to address the challenges of learning hierarchical, time-varying, multi-dimensional state space models for dynamic objects and phenomena, especially in the presence of noisy measurements, complex backgrounds, and calibration errors. Research directions may include learning models for radar detection in complex environments, developing birth and trajectory models to enhance detection and tracking, and exploring semi-supervised or unsupervised training of sensor data classifiers. The successful candidate will have the flexibility to steer the research focus based on engineering impact and personal interests.

Supervision is provided by Dr M Uney, an expert in signal processing, machine learning, probabilistic models, and Bayesian computation for sensor fusion and information processing. Prof Mike Davies, holding the Jeffrey Collins Chair in Signal and Image Processing, contributes expertise in machine imaging, computational sensing, and sensor fusion. The research environment is highly interdisciplinary, spanning machine learning, electrical and electronic engineering, robotics, and applied mathematics.

The position is open to UK/EU and international applicants. Funding includes an annual stipend of £21,935 (2024-25 fiscal year, subject to revision) for 3.5 years, plus £5000 research expense funds. Tuition fees are covered for all eligible students. UK nationals and eligible applicants may align the studentship with the Sensing, Processing and AI for Defence and Security Centre for Doctoral Training (SPADS CDT), potentially receiving an enhanced stipend subject to CDT approval and security clearance. Applicants should indicate their interest in the CDT in their Personal Statement and review eligibility criteria on the provided links.

Applicants should have a strong academic background in engineering, mathematics, computer science, or related fields, with experience in machine learning, signal processing, probabilistic modeling, or Bayesian computation preferred. Standard University of Edinburgh PhD entry requirements apply. Applications are welcomed from self-funded students or those seeking scholarships from the University of Edinburgh or elsewhere.

The application deadline is March 15, 2026. For more information and to apply, visit the University of Edinburgh’s postgraduate research portal and the project webpage. Contact the School of Engineering for further details if required.