Therapists’ Force-Profile Teach-and-Mimic Approach for Upper-Limb Rehabilitation Exoskeletons


Loading...

Date

2024-11

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

In this work, we propose a framework enabling upper-limb rehabilitation exoskeletons to mimic the personalised haptic guidance of therapists. Current exoskeletons face acceptability issues as they limit physical interaction between clinicians and patients and offer only predefined levels of support that cannot be tuned during the movements, when needed. To increase acceptance, we first developed a method to estimate the therapist’s force contribution while manipulating a patient’s arm using an upper-limb exoskeleton. We achieved a precision of 0.31Nm without using direct sensors. Then, we exploited the Learning-by-demonstration paradigm to learn from the therapist’s interactions. Single-joint experiments on ANYexo demonstrate that our framework, applying the Vector-search approach, can record the joint-level therapist’s interaction forces during simple tasks, link them to the kinematics of the robot, and then provide support to the user’s limb. The support is coherent with what is learnt and changes with the real-time arm kinematic configuration of the robot, assisting whatever movement the patient executes in the end-effector space without the need for manual regulation. In this way, robotic therapy sessions can exploit therapists’ expertise while reducing their manual workload.

Publication status

published

Editor

Book title

Volume

6 (4)

Pages / Article No.

1658 - 1665

Publisher

IEEE

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Rehabilitation robots; Vector-search; Therapist support; Learning by demonstrations

Organisational unit

03654 - Riener, Robert / Riener, Robert check_circle

Notes

Funding

Related publications and datasets