1. Home »
  2. Supervisor: Dr. Nadia Sultan
Supervisor: Dr. Nadia Sultan

 

 AI-Driven Adaptive Prosthetics: Reinforcement Learning and Predictive Control for Personalized Mobility Solutions

 

Supervisor: Dr. Nadia Sultan, Assistant Professor

Campus/School/Dept:Department of Electrical Engineering  Center of Excellence in AI (CoE_AI) BUIC

RAC Approved Supervisor for Research Areas:

  • Control Systems,
  • Robotics & AI

Supervisory Record:  

  • PhD Produced: 0
  • PhD Enrolled:0
  • MS/MPhil Produced: 6
  • MS/MPhil Enrolled: 2

 

Topic Brief Description:

The adaptability of prosthetics and exoskeletons to user-specific physiological patterns and dynamic environments remains a significant challenge. Current systems predominantly use predefined, rigid control models, limiting their ability to adjust to variations in user behavior, fatigue, and external conditions. This lack of adaptability often leads to suboptimal performance, discomfort, and reduced user engagement. By leveraging Artificial Intelligence (AI), specifically reinforcement learning (RL) and predictive control frameworks such as Model Predictive Control (MPC) etc., it is possible to create systems capable of real-time learning and adaptation. However, challenges in integrating reinforcement learning with robust predictive control, managing computational constraints on wearable devices, and ensuring secure and ethical use of user data need to be addressed.

 

Research Objectives/Deliverables:

  1. To develop reinforcement learning-based adaptive control algorithms for upper/ lower-limb prosthetics / exoskeletons that enhance real-time responsiveness to user needs.
  2. To integrate predictive control (MPC) techniques for robust gait optimization and stability across varying terrains.
  3. To design predictive models capable of estimating user fatigue, performance degradation, and safety risks in real-time.
  4. To implement energy-efficient methods for processing user data and training adaptive AI models.
  5. To validate the system through simulations, measuring improvements compared to conventional systems.

 

Research Questions: 

  1. How can reinforcement learning and predictive control be combined to optimize user-specific adaptation in prosthetics and exoskeletons?
  2. What predictive analytics techniques can be used to model user fatigue, performance, and risk factors during operation?
  3. How can computational efficiency and real-time decision-making be achieved for AI-powered prosthetics and exoskeletons?
  4. How does the integration of AI-driven adaptive systems impact user satisfaction, long-term engagement, and rehabilitation outcomes?

 

Candidate’s Eligibility Profile:

  1. The applicant must have an MS/MPhil/Equivalent degree in electrical engineering with CGPA >0. Besides, applicants must have a strong background in control systems, AI, mathematics, optimization theory and related fields.
  2. Experience with programming languages such as MATLAB, Simulink and Python is advantageous. Candidates should thrive in an international environment and have excellent communication skills to actively contribute to team research efforts.
  3. Proficiency in spoken and written English is essential. We value independence and responsibility while promoting teamwork and collaboration among colleagues.