DC11: Experience-Driven Co-Adaptation through Multi-Agent Learning in Assistive Devices
Project: Experience-Driven Co-Adaptation through Multi-Agent Learning in Assistive DevicesĀ (WP3)
Host institution: LUH (Germany)
Supervisor: Prof. Thomas Seel (LUH, Germany)
Co-supervisor(s): Prof. Robert Riener (ETH), Eng. F. Salsedo
Objectives:
Implement multi-agent learning and explore the transfer of common data and experiences between individual systems and users.
Expected Results:
Establishing a collaborative network for sharing data and experiences among assistive health systems, with a focus on demonstrating effectiveness in key factors for generating genuine symbiotic interactions, such as environmental awareness and task differentiation.
Planned secondment(s):
- ETH (3 months, M21-M23): Applying and optimizing learing methods to improve co-adaptaion at the sensorimotor systems lab, with R. Riener. (KPI: joint conference paper)
- WR (3 months, M32-M34): Investigating and integrating cooperative learning methods into wearable assistive robotic systems, with A. Filippeschi (KPI: joint journal paper)
Enrolment in Doctoral degree: Doctoral School of Leibniz University Hannover (Germany)
Required profile: Background in control systems and machine learning, experience with Matlab or Python or both
Desirable skills/interests: Prior knowledge on multi-agent systems and biomechanics, interest in biomedical engineering and exoskeletons