Associate Professor in Medical Robotics and Industrial Automation
Dr Hajiyavand works on the design and development of automated systems, use of robotics and applications of Artificial Intelligence within robotics for inspections, and robotics for manipulation and micromanipulation.
Dr Amir Hajiyavand’s research advances intelligent robotics, automation, and Artificial Intelligence (AI) to address real-world challenges in manufacturing, healthcare, and the Circular Economy. His work integrates robotics, computer vision, smart sensing, and AI to develop autonomous systems that operate safely, efficiently, and reliably in complex environments.
His research covers robotic manipulation, industrial automation, inspection, precision robotics, human–robot collaboration, and AI-enabled autonomous systems. Applications include automated inspection and quality assurance, advanced manufacturing, micromanipulation, healthcare technologies, and sustainable manufacturing.
Robotics for Healthcare is an important area of his research, focusing on the development of intelligent and precision robotic technologies to support healthcare professionals and improve patient outcomes. His work explores AI-enabled robotic systems, medical robotics, precision manipulation, smart sensing, and human–robot interaction for healthcare applications. A particular emphasis is placed on developing safe, reliable, and clinically relevant technologies that can translate from research into practical healthcare settings.
A key focus is translating scientific advances into practical industrial solutions. Working closely with industry partners, he develops robotic technologies that are scalable, reliable, economically viable, and aligned with end-user needs. He has also been working with the West Midlands Combined Authority (WMCA) to support the adoption of robotics and automation across a range of industries. He is a Steering Group Member of the West Midlands Robotics & Autonomous Systems Cluster (WM-RAS), contributing to regional innovation, collaboration, and technology adoption.
Dr Hajiyavand leads and contributes to multidisciplinary research collaborations across the UK and internationally. His work spans the full range of Technology Readiness Levels (TRLs), from early-stage concepts to real-world deployment, with the aim of improving productivity, precision, sustainability, and quality of life.
Assistant Professor
Dr Jiaqi Ye'd research focuses on perception and intelligence for robotic and autonomous systems, integrating machine vision, multi-modal sensing, and deep learning for robust real-world engineering applications.
Dr Jiaqi is an Assistant Professor in Robotics and AI in the Department of Mechanical Engineering at the University of Birmingham, where he co-leads the PRIME Lab. His research interests include laser and camera systems, machine vision, deep learning algorithms, and robotic perception. His work focuses on developing universal perception frameworks that enable robust and accurate perception, as well as perception-driven planning, for robots and autonomous systems in complex engineering environments.
MTC Chair in Sustainable Manufacturing
Professor Butler is currently the MTC Chair in Sustainable Manufacturing and lead the Sustainable Manufacturing Group within the School of Engineering, University of Birmingham.
David Butler is currently the Manufacturing Technology Centre Professor in Sustainable Manufacturing. Prior to rejoining Birmingham (where he obtained his degrees in Metrology, Quality Systems, Manufacturing Engineering, and Economics), David was based in the University of Strathclyde where he held concurrent appointments with the National Physical Laboratory and the National Manufacturing Institute Scotland. David spent 18 years in Singapore where his interest in robotics grew through several industrial funded projects in areas including building cells for robotised propellor finishing and automated welding for oil & gas, and developing a remote operated dry ice cleaning solution using an in-house designed crawler robot.
David has recently led a West Midlands Combined Authority/Innovate UK funded project on promoting adoption of robots and automation in local SMEs (RAMP) and sits on the board of the West Midlands Robotics & Autonomous Systems Cluster (West Midlands RAS Cluster).
Interests: automation for recycling, decommissioning, and inspection.
Associate Professor in Computer Science
Dr Hyung Jin Chang is an Associate Professor in Computer Science at the University of Birmingham. His research focuses on human-centred AI and computer vision for intelligent and interactive robotic systems.
Dr Hyung Jin Chang is an Associate Professor in the School of Computer Science at the University of Birmingham and is affiliated with the Institute of Data and Artificial Intelligence (IDAI). He was also a University Turing Fellow of the Alan Turing Institute, the UK’s national institute for data science and artificial intelligence.
He received his BSc in Electrical and Computer Engineering and PhD in Electrical Engineering and Computer Science from Seoul National University in 2006 and 2013, respectively. Before joining the University of Birmingham, he worked as a Post-Doctoral Research Associate at Imperial College London, where he participated in several European research projects focusing on computer vision, machine learning, and human-robot interaction.
Dr Chang’s research lies at the intersection of artificial intelligence, computer vision, robotics, and human-robot interaction, with a particular emphasis on human-centred AI. His work aims to build intelligent robotic systems capable of understanding human perception, action, and intention through visual and multimodal learning.
He is especially interested in human-centred visual learning, including the estimation of human hand pose, body pose, and gaze, and the modelling of human actions and internal states. His broader goal is to advance robot vision and learning for intelligent and natural human–robot interaction.
Assistant Professor
Staff profile for Dr Mingchao Liu, University of Birmingham
Dr Mingchao Liu is an Assistant Professor in Mechanical Engineering at University of Birmingham. His research centres on the nonlinear mechanics of flexible slender structures, exploring how their large deformation, instability, and dynamics can be harnessed to achieve adaptive and programmable mechanical behaviours. He applies these principles to the design of morphing structures, mechanical metamaterials, and soft robotic systems that can reconfigure and interact intelligently with their environments.
Teaching Fellow in Law
Biographical and contact information for Angela Eggleton, Teaching Fellow in Law at the University of Birmingham
Angela’s research interests span a range of interdisciplinary and emerging areas, including emerging technologies, robotics, healthcare, environmental law, electric vehicles, the circular economy and intellectual property.
Angela has published widely across these areas. Most recently, she co-edited a book on patient safety law, ethics and the NHS, published by Routledge. Her previous publications include a chapter with Edward Elgar arising from her research into artificial intelligence and robotics, as well as an article for the University of Oxford’s Centre for Socio-Legal Studies blog exploring her robotics research.
As part of a NERC-funded project examining robotics and law, Angela organised and led an interdisciplinary conference at the University, bringing together participants from industry, academia and government from across the UK.
Angela has also contributed to the Faraday Institution’s ReLiB project, which focuses on the recycling and reuse of lithium-ion electric vehicle batteries. Through this work, she engaged with the European Commission in Brussels and collaborated with researchers across several universities and disciplines, including business, economics, metallurgy and materials science. Her involvement reflects the interdisciplinary nature of her research and her experience of working across academic, policy and industry contexts.
Shazad Ashraf is a Consultant Colorectal Surgeon and Clinical Director of Research and Development at University Hospitals Birmingham. He is also Honorary Professor of Surgical Engineering at the University of Birmingham.
His work focuses on the development, clinical evaluation and responsible implementation of artificial intelligence, surgical technologies and digital diagnostic systems to improve patient safety, healthcare efficiency and clinical outcomes.
He leads and contributes to several major collaborative programmes, including COBIx, a national NHS study evaluating AI-assisted digital pathology, and TEMSET-24K, a large-scale surgical video dataset developed to support the training and validation of surgical AI models. He also co-developed RAPTOR, an AI-enabled triage and pathway-optimisation platform presented at MICCAI, supporting the prioritisation and management of patients across colorectal cancer pathways.
Shazad completed his DPhil at the University of Oxford and subsequently held an Academic Clinical Lectureship within the Nuffield Department of Surgical Sciences, where his research focused on antibody engineering and its translation into clinical practice.
As a Birmingham Health Partners Fellow and NHS Responsible AI Champion, he works across the NHS, academia and industry to advance the ethical, secure, clinically effective and scalable adoption of artificial intelligence within healthcare.
Using a custom manually labelled dataset of ~2k images of strawberry farms to enable autonomous strawberry harvesting with a mobile robot. Focusing specifically on navigation, strawberry detection, ripeness estimation and localisation.
The surge in medical waste has highlighted the urgent need for cost-effective and advanced management solutions. In this project, a novel medical waste management approach, "MedBin," is proposed for automated sorting, reusing, and recycling. A comprehensive medical waste dataset, "MedBin-Dataset" is established, comprising 2,119 original images spanning 36 categories, with samples captured in various backgrounds. The lightweight "MedBin-Net" model is introduced to enable detection and instance segmentation of medical waste, enhancing waste recognition capabilities. Experimental results demonstrate the effectiveness of the proposed approach, achieving an average precision of 0.91, recall of 0.97, and F1-score of 0.94 across all categories with just 2.51 M parameters (where M stands for million, i.e., 2.51 million parameters), 5.20G FLOPs (where G stands for billion, i.e., 5.20 billion floating-point operations per second), and 0.60 ms inference time. Additionally, the proposed method includes a World Health Organization (WHO) Guideline-Based Classifier that categorizes detected waste into 5 types, each with a corresponding disposal method, following WHO medical waste classification standards. The proposed method, along with the dedicated dataset, offers a promising solution that supports sustainable medical waste management and other related applications. Access the MedBin-Dataset samples. See the source code for MedBin-Net.
Watch the SLICK robotic retrieval demonstration.
Hamid Mirshekarlou is a doctoral researcher specialising in medical robotics, with a focus on optimising robotic-assisted injection and penetration procedures. His research aims to enhance precision, reduce patient trauma, and minimise tissue deformation through advanced control strategies and biomechanical modelling. By integrating optimisation techniques with Software Simulation and experimental validation, he strives to develop safer, more efficient robotic systems that improve clinical outcomes in minimally invasive medical interventions.
Qiufeng Yi is a PhD researcher at the University of Birmingham, specialising in the application of artificial intelligence to medical image analysis and health data processing. His research covers disease diagnosis, image segmentation, structured report generation, cross-modal modeling, and extends to automated detection and surgical assistance systems.
Chenyang Wan is currently working on AI and medical image analysis. Projects include:
Yasaman Khanbaba is currently working on bio-robotics and magnetic control systems. Projects include:
Robotic systems are designed to improve medical diagnostic procedures, surgical methods and treatment techniques, along with enhancing medical-device testing and evaluation.
Using automatic systems revolutionises the medical industry by bringing consistency and high accuracy to the current manual operations. This research will focus on developing an automated system using vision-based recognition software to provide precise information to conduct medical procedures. This research includes designing the automated system using robot arms which uses machine-learning algorithms to operate a medical procedure and increase accuracy during the patient-related operation. This includes operational task planning, vision-based image analysis, developing robotic interfaces and control, programming, and testing and validating the results.
Additionally, Melike is working on automating processes with robot arm in various fields.
Anoop Singh is currently working on a project exploring bias in healthcare AI systems, particularly those using physiological and wearable sensor data. The research examines how hidden differences in data quality, labelling, and system behaviour can lead to unequal performance across different user groups. This is especially important in healthcare, where such issues can directly impact real world outcomes. The aim is to better understand and address these challenges to support the development of more reliable and fair AI systems.
Reuben Blakeway is a robotics researcher focusing on multimodal, heterogeneous robot teams, especially aerial–ground pairings, which collaborate to traverse complex terrain. Reuben's work combines pragmatic hardware integration with transparent, resource-constrained perception and control, unifying complementary sensing and actuation across platforms into a coherent, deployable stack. A central theme is cooperative mobility, including tether-assisted anchoring and other mechanisms by which one modality extends another’s capabilities. The aim is to advance beyond lab prototypes to field-ready systems and to distil reproducible engineering patterns and software artefacts for reliable, adaptable deployments.
Elliott Dyson's research focuses on automating medical waste recycling with robotic arms and deep learning (AI) for image understanding, planning, and control. He is building a hierarchical system that runs at two rates: a slower network for perception and long-horizon planning, and a faster network for low-latency, accurate joint control. The goal is a reliable, interpretable pipeline that can recognise, sort, and manipulate medical-waste items in real settings.
Almuthana Alfaouri's research explores the integration of artificial intelligence, robotics, and laboratory automation into assisted reproductive technologies (ART). He is particularly focused on how machine learning and robotic micromanipulation can enhance precision and reproducibility in embryology and microsurgery, improving both workflow efficiency and clinical outcomes. In addition, he is developing AI models for the recognition and interpretation of hysterosalpingography (HSG) and ultrasound imaging in reproductive medicine. Ultimately, his goal is to contribute to a future where advanced technologies transform laboratory practice and expand the possibilities of reproductive care.
Hospital environments can be stressful for patients, staff and visitors. Nurses, doctors and other care providers are supporting multiple patients, who may not fully understand their situation, and may be frightened. Family members of these patients may be equally concerned if they do not understand treatments given, what different status readouts may mean, or may even be trying to find their loved one when they have moved ward.
The solution to all three is a physical healthcare assistant, utilising modern Artificial Intelligence Models to converse with individuals. These models are not only verbal (like Large Language Models) but also visual. By running age recognition, a unit can decide if the person it is speaking to is a child or adult, and tailor its response. By recognising what uniforms medical staff wear, the unit can decide how much information to divulge, and by ensuring an approachable aesthetic is used, the unit can comfort people when they are scared.
Levi Yu is currently working across two projects within medical and patient monitoring applications. The first involves implementing a 3D Systems Touch haptic device to provide intuitive force feedback control of a robotic arm, enabling precise, tactile-guided interaction for medical and patient monitoring use cases. Alongside this, he is developing and integrating a patient monitoring user interface for a mobile platform, delivering real-time data in an accessible, responsive format to support healthcare professionals at the point of care.
Investigating alternative legged robot architectures for highly stable, high-capacity multi-role agricultural platforms. The research covers end-to-end system development, from mechanical design and embedded hardware to actuation, power electronics, software, and control, with an emphasis on integrated in-house solutions.
