Learning Control and Its Application in Rehabilitation Robotics
Prof. Ying Tan
The University of Melbourne
摘要:
Rehabilitation robotics draws from the principle of "practice makes perfect," utilizing repetitive tasks to aid in motor re-learning and functional recovery, especially in poststroke rehabilitation. Rooted in neurocognitive rehabilitation theories, this concept has spurred the development of robot-assisted therapies, offering tailored, intensive task routines for individual patient needs.
Leveraging advancements in learning control (LC) strategies, initially devised for achieving high tracking performance in industrial settings since 1978, emerges as a natural choice for controller designs in rehabilitation robotics. Unlike traditional control algorithms, LC algorithms harness information from previous iterations to enhance performance in subsequent ones. This presentation highlights cutting-edge developments in LC designs and demonstrates how various LC algorithms address the complex challenges in rehabilitation robotics. Furthermore, it explores opportunities for integrating learning control into rehabilitation robotics and identifies key research questions to drive control-theoretic advancements in this field.
--
FROM 202.120.11.*