Chapitre D'ouvrage Année : 2024

Electrophysiological Measures for Human–Robot Collaboration Quality Assessment

Résumé

Electrophysiological signals offer invaluable insights for human monitoring, providing real-time, objective measures of mental states. Among the sensors used for signal acquisition, electrocardiography (ECG) and electrodermal activity (EDA) sensors stand out for their affordability and wearability. Electroencephalography (EEG) is also gaining popularity, particularly with the advent of dry electrode devices that reduce setup times, albeit at the expense of signal quality. These signals are increasingly employed to close the loop and develop adaptive systems, a discipline known as physiological computing (Fairclough, Interact Comput 21(1–2):133–145, 2009). For example, cerebral activity can be used as an active brain–computer interface to control a robotic arm (Jeong et al. IEEE Trans Neural Syst Rehab Eng 28(5):1226–1238, 2020). Yet, the field of electrophysiological computing extends beyond mere control. It facilitates the monitoring of human mental states during tasks, which is of significant interest in Human–Robot Collaboration (Roy et al., Robotics 9(4):100, 2020). A robot equipped to monitor human mental states could dynamically adjust its behavior to uphold an optimal quality of interaction, addressing various aspects such as performance, engagement, satisfaction, or security. Moreover, it could learn from the impact of each action on the user’s mental state, enabling more informed decision-making. Mental state monitoring has already been applied to several kinds of Human–Robot Interaction (HRI), including teleoperation and error correction (Lopes-Dias et al., Sci Rep 9(1):1–9, 2019). Nevertheless, integrating physiological computing with human–robot collaboration presents unique challenges. Thus, the aim of this chapter is to review advanced applications of physiological computing in the domain of human–robot collaboration and offer guidance to researchers interested in delving into this interdisciplinary domain. It will develop the advantages of mental state monitoring in human–robot collaboration, examine cutting-edge studies employing such setups, as well as offer practical guidelines based on these findings.
Fichier principal
Vignette du fichier
Springer_Nature_Chapter_overleaf.pdf (276.06 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04883459 , version 1 (13-01-2025)

Identifiants

Citer

Mathias Rihet, Guillaume Sarthou, Aurélie Clodic, Raphaelle Roy. Electrophysiological Measures for Human–Robot Collaboration Quality Assessment. Discovering the Frontiers of Human-Robot Interaction, Springer Nature Switzerland, pp.363-380, 2024, 978-3-031-66655-1. ⟨10.1007/978-3-031-66656-8_15⟩. ⟨hal-04883459⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More