Work

Adapting Interaction Control in Robot-Aided Rehabilitation Using Reinforcement Learning

Year: 2024

Type: conference-paper

Abstract: Adapting control strategy parameters in robot-aided rehabilitation is an important task to enhance the patients' engagement and recovery. Thus, this work investigated the feasibility of applying a Reinforcement Learning algorithm to automatize the learning process. A Q-learning algorithm dynamically adjusts the interaction stiffness taking as input the motor performance and physiological state of the user. The experiments demonstrated the feasibility of the proposed approach and the ε-greedy capability in learning an optimal policy.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.14731060

Authors: Molle, Rita, Tamantini, Christian, Lauretti, Clemente, Romano, Emilio Maria, Zollo, Loredana

Language: English

Topic: Prosthetics and Rehabilitation Robotics

Subfield: Biomedical Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

OpenAlex ID: W6967977932

FWCI:

Cites:

Cited by:

Related to: