PhD Engineering Scholarship: Advanced Human Interfacing Technology and Machine Learning Methods for Real-Life Assistive Robotic Exoskeleton

The progress on advanced signal processing techniques and machine learning algorithms allows us to non-invasively interface with our central nervous system using sensors such as high-density surface electromyographic recordings (HDsEMG). The recorded HDsEMG signals can be decoded into motor unit activities, which later can be translated into user intension and control signals for external assistive devices such as robotic exoskeletons. At this moment, it is still challenging to achieve effectivedecoding and control of an exoskeleton in real-life scenario partially due to the interaction between the robotic system and the human user. For instance, an assistive force applied by the exoskeleton may at the same time help the user in achieving certain motion, but may also deform the skin and generate artificial EMG signals, which later affects user intension prediction accuracy. It is therefore critical to address the artifacts generated due to human robot interaction, and further improve the prediction accuracy to achieve natural and effective robot assisted motion. 

To tackle such challenge, the student will first integrate existing human interfacing equipmentlocated at the Neuromechanics and Rehabilitation Technology group at Imperial College London, and develop a testing platform to examine the influence of exoskeleton assisted motion upon electrophysiological signals such as the HDsEMG signal foruser intension decoding quality. Aside from passively evaluating signal quality and proposing structural or design improvements, the student should also actively examine the artifacts generated by the robot, and propose machine learning methods/algorithms to compensate such influence. Detailed approach can later be discussed among the student and the supervisors.

Due to the complexity of the research, the student should be self-motivated and heavily interested in related research including human-robot interaction, assistive technology, robotics, electrophysiology, body biomechanics and ideally real-time Simulink systems for robotic control. The student is expected to travel between labs at University of Sussex and Imperial College London and collaborate with various researchers in experiments. It is therefore critical for the student to be respectful and kind to other lab members. Furthermore, effective communication skills in both oral and written are demanded for this position due to again the nature of cross-institute collaboration. 

Eligibility

This scholarship is available to UK, EU and overseas applicants. 

Eligible candidates will have an upper second-class (2:1) undergraduate honours degree (or equivalent qualification) in a related field. 

The University of Sussex believes that the diversity of its staff and student community is fundamental to creative thinking, pedagogic innovation, intellectual challenge, and the interdisciplinary approach to research and learning. We celebrate and promote diversity, equality and inclusion amongst our staff and students. As such, we welcome applicants from all backgrounds.

Deadline

26 June 2024 23:45

How to apply

Apply online for a full time PhD in Engineering (JAN2025) using our step-by-step guide.

Please clearly state on your application that you are applying for the Advanced Human Interfacing Technology and Machine Learning Methods for Real-Life Assistive Robotic Exoskeleton scholarship under the supervision ofDr Hsien-Yung Huang.

Please ensure you application includes each of the following: 

• A personal statement.
• Your CV.
• Degree certificates and transcripts.
• 2 references, including a minimum of 1 from any institution studied at within the last 5 years.
• If your first language is not English you will need to demonstrate that you meet the University’s English language requirements, see here for details of our accepted documentation.
• Optional: Research proposal.

Contact us

For general enquiries, please email phd.engineering@sussex.ac.uk. 

For project specific queries, please email HsienYung.Huang@sussex.ac.uk.