# Multimodal Evaluation of Mental Workload and Engagement in Upper-Limb Robot-Assisted Motor Tasks

## TL;DR

This study explores how mental workload and engagement change during robot-assisted upper-limb rehabilitation using brain and heart signals and questionnaires.

## Contribution

A novel multimodal approach is proposed to evaluate mental workload and engagement in robotic rehabilitation.

## Key findings

- Engagement increased significantly when subjects listened to music compared to a metronome.
- Passive assistance was perceived as less demanding and less engaging than active or semi-assisted conditions.
- ECG metrics aligned with subjective measures, while EEG did not show significant variation across assistance modalities.

## Abstract

Patient engagement and mental workload (MWL) are often overlooked when optimising robotic-assisted rehabilitation, despite their potential impact on its effectiveness. This study aims to propose a multimodal approach to assess MWL and engagement, using electrophysiological signals and questionnaires, to explore their modulation across different assistance modalities and engaging strategies. Thirty healthy subjects were enrolled and performed repetitive upper-limb movements with a robotic device under three assistance modalities (active, passive, semi-assisted) while listening to a 1 Hz auditory stimulus (metronome or music). Electroencephalography, Electrocardiogram, the NASA Task Load Index, and the Short Stress State Questionnaire were used to assess objective and perceived MWL and engagement. Engagement increased significantly in the music condition, whereas MWL showed no significant change. The passive modality was perceived as significantly less demanding and less engaging compared to active and semi-assisted conditions. Although EEG objective indicators did not vary across modalities, the ECG objective metric was modulated significantly in agreement with the subjective measures. Overall, the auditory stimulus significantly influenced engagement, and assistance levels affected both perceived mental demand and engagement. The proposed multimodal approach is sensitive to both engagement and MWL constructs, highlighting the potential for adaptive rehabilitation systems designed to maintain engagement, prevent overload or monotony, and ultimately support better functional outcomes over the long term of robotic training.