In this paper we present a general framework for affective human-robot interaction that allows users to intuitively interact with a robot and takes into account their mental fatigue, thus simplifying the task or providing assistance when the user feels stressed. Interaction with the robot is achieved by naturally mapping user's forearm motion, detected with a smartwatch, into robot's motion. High-level commands can be provided by means of gestures. An approach based on affective robotics is used to adapt the level of robot's autonomy to the cognitive workload of the user. User's mental fatigue is detected from the analysis of heart rate, also measured by the smartwatch. The framework is general and can be applied to different robotic systems. In this paper, we consider its experimental validation on a wheeled mobile robot.
A Framework for Affect-Based Natural Human-Robot Interaction / Villani, Valeria; Sabattini, Lorenzo; Secchi, Cristian; Fantuzzi, Cesare. - (2018), pp. 1038-1044. (Intervento presentato al convegno 27th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2018 tenutosi a The Jiangsu International Conference Center, 307 Zhongshan East Road, chn nel 2018) [10.1109/ROMAN.2018.8525658].
A Framework for Affect-Based Natural Human-Robot Interaction
Villani, Valeria
;Sabattini, Lorenzo;Secchi, Cristian;Fantuzzi, Cesare
2018
Abstract
In this paper we present a general framework for affective human-robot interaction that allows users to intuitively interact with a robot and takes into account their mental fatigue, thus simplifying the task or providing assistance when the user feels stressed. Interaction with the robot is achieved by naturally mapping user's forearm motion, detected with a smartwatch, into robot's motion. High-level commands can be provided by means of gestures. An approach based on affective robotics is used to adapt the level of robot's autonomy to the cognitive workload of the user. User's mental fatigue is detected from the analysis of heart rate, also measured by the smartwatch. The framework is general and can be applied to different robotic systems. In this paper, we consider its experimental validation on a wheeled mobile robot.File | Dimensione | Formato | |
---|---|---|---|
18ROMANb.pdf
Accesso riservato
Tipologia:
Versione pubblicata dall'editore
Dimensione
5 MB
Formato
Adobe PDF
|
5 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
5_A_framework_For.pdf
Open access
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
4.95 MB
Formato
Adobe PDF
|
4.95 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris