| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 5.97 MB | Adobe PDF |
Advisor(s)
Abstract(s)
Rehabilitation is a relevant process for the recovery from
dysfunctions and improves the realization of patient's Activities of Daily
Living (ADLs). Robotic systems are considered an important field within
the development of physical rehabilitation, thus allowing the collection of
several data, besides performing exercises with intensity and repeatedly.
This paper addresses the use of a collaborative robot applied in the rehabilitation
field to help the physiotherapy of upper limb of patients, specifically
shoulder. To perform the movements with any patient the system
must learn to behave to each of them. In this sense, the Reinforcement
Learning (RL) algorithm makes the system robust and independent of
the path of motion. To test this approach, it is proposed a simulation
with a UR3 robot implemented in V-REP platform. The main control
variable is the resistance force that the robot is able to do against the
movement performed by the human arm.
Description
Keywords
Robotics rehabilitation Collaborative robots Simulation Reinforcement learning algorithm
Citation
Fernandes, Lucas de Azevedo; Lima, José; Leitão, Paulo; Nakano, Alberto Yoshiro (2020). Using a collaborative robot to the upper limb rehabilitation. In 4th Iberian Robotics Conference, ROBOT 2019; Porto. p. 429-440. ISBN 978-3-030-35989-8