Privacy-Preserving AI for Mental Health Detection in Care Robotics

This project addresses the challenge of developing a privacy-preserving, AI-based Large Language Model (LLM) system capable of detecting anxiety and depression in care robotics settings, while ensuring safe, trustworthy, and clinically aligned interactions. Socially assistive robots are already demonstrating measurable benefits in elderly care, rehabilitation, and emotional well-being. However, current AI-driven systems often lack trustworthiness, robust privacy safeguards, and clinically validated response mechanisms when handling sensitive mental-health data. Issues such as misinformation, hallucination, emotional dependency, and data leakage highlight the urgent need for safer and more ethical AI solutions. The project will develop a lightweight LLM fine-tuned for anxiety and depression detection, a role-based privacy framework controlling information access for patients, clinicians, and caregivers, and clinically guided responses aligned with NHS pathways. The system will be deployed on advanced robotic platforms (such as Care-O-Bot) and embedded systems (e.g., Nvidia Jetson). The research adopts a multi-layered methodology using ethically sourced mental-health datasets compliant with GDPR, ensuring real-world applicability across healthcare settings. The successful applicant will also undertake Graduate Teaching Assistantship (GTA) duties, contributing up to 180 hours of teaching or research support per academic year as part of the scholarship.

Applicants should hold at least a 1st or 2:1 Honours degree in AI and/or Cybersecurity or a related discipline. English language requirements of IELTS 7 with a minimum score of 6.5 in all test areas (or equivalent) if English is not your first language. Applications encouraged from underrepresented groups including women, LGBTQ+, and minoritised ethnicities.

Apply via the Sheffield Hallam University online application form. Applications must include:
A personal statement (up to 2 pages) detailing your interest in the project and relevant experience, demonstrating motivation for research, analytical and technical expertise, communication ability, planning skills, ability to work independently and collaboratively, commitment to integrity, resilience, and potential teaching contributions.
A two-page CV.
Two letters of reference (at least one academic, both dated within the last 2 years).
Copy of your highest degree certificate and transcript.
Non-UK applicants must submit IELTS results taken in the last two years and a copy of their passport.
If applying for multiple GTA projects, list them all and submit a tailored personal statement for each.