Robotic-Assisted AI for Rehabilitation: Adaptive Control Based on Patient Feedback Loops

Robotic-Assisted AI for Rehabilitation: Adaptive Control Based on Patient Feedback Loops

Rehabilitation is a crucial stage in recovering motor function after stroke, neurological injury, or musculoskeletal trauma. However, traditional rehabilitation methods often lack personalization, are resource-intensive, and fail to offer continuous feedback adapted to the patient’s evolving condition. In underserved or aging populations, access to qualified physiotherapists is further limited. Robotic-assisted rehabilitation offers a promising alternative, but existing systems tend to follow predefined motion paths without adapting to real-time patient feedback or physiological signals.

This doctoral project proposes the development of an intelligent, collaborative robotic system powered by hybrid AI, combining bio-inspired algorithms, machine learning, and symbolic reasoning. The robot will integrate real-time electromyography (EMG) signals from the patient’s muscles to assess effort, detect fatigue, and adapt its assistance accordingly. Deep learning models (e.g., CNNs for EMG pattern recognition) will work alongside symbolic rules (e.g., movement safety protocols) to enable adaptive, explainable, and safe control of the robot’s motion.

Candidates are expected to carry out their research full-time within the structures of EUROMED University.

• Design and develop a collaborative robotic rehabilitation platform, integrating EMG sensors, motion sensors (IMU), and human–robot interfaces.

• Implement deep learning models (e.g., CNN, LSTM) for muscle pattern recognition and fatigue estimation.

• Develop an adaptive control strategy combining machine learning with symbolic reasoning to adjust robotic assistance in real time.

• Establish intelligent feedback loops between the patient and the robot to ensure continuous, safe, and personalized interaction.

• Conduct experimental validation on test benches and motion simulators to assess system robustness, safety, and performance.

• Contribute to scientific dissemination through publications in international conferences and journals, and to the valorization of research outcomes.

The ideal candidate should hold a Master’s or Engineering degree in Robotics, AI, or related fields, with strong skills in Python, C++, and robotic platforms (ROS/ROS2, Gazebo, MATLAB/Simulink). A solid background in machine learning (TensorFlow, PyTorch, Scikit- learn) and a strong interest in intelligent healthcare systems are required. Analytical thinking, autonomy, teamwork, and fluency in English and French are essential.

CV, a cover letter, the PhD project, diplomas, and academic transcripts.

The application file must be sent to the Doctoral Studies Center (CEDoc) of the Euro-Mediterranean University of Fes by email no later than October 24, 2025, to the following contacts:

Administrative Affairs Officer of the CEDoc: Mrs. Boutaina Jai Mansouri : : b.jai-mansouri@emadu.ueuromed.org)

Director of Research and of the CEDoc: Prof. Abdelghafour Marfak : : a.marfak@euromed.org)

• Pr. ELKARI Badr (b.elkari@ueuromed.org)