We present a programming-by-demonstration framework that allows users to simultaneously teach both motion and compliance behaviors to collaborative robots. The system integrates a wearable surface electromyography interface and real-time vibrotactile feedback into the kinesthetic teaching process, enabling intuitive point-by-point modulation of robot’s mechanical compliance. Unlike prior methods that focus solely on trajectory or symbolic control, our approach leverages unsupervised co-contraction estimation for continuous impedance shaping, without the need for explicit offline procedures or labeled data. To validate the method, we redesigned and conducted two contact-rich tasks—industrial wiring and a welding-like operation—demonstrated by ten subjects using a 7-degrees of freedom (DOF) collaborative manipulator. Results show that users could effectively program both trajectory and compliant interaction behaviors, highlighting the framework’s potential for intuitive and robust human–robot collaboration.
Meattini, R., Govoni, A., Galassi, K., Chiaravalli, D., Palli, G., Melchiorri, C. (2025). Programming Robot Interaction Behavior During Kinesthetic Teaching Exploiting sEMG-Based Interfacing and Vibrotactile Feedback. IEEE/ASME TRANSACTIONS ON MECHATRONICS, 30(5), 4011-4022 [10.1109/tmech.2025.3603402].
Programming Robot Interaction Behavior During Kinesthetic Teaching Exploiting sEMG-Based Interfacing and Vibrotactile Feedback
Meattini, Roberto
;Govoni, Andrea;Galassi, Kevin;Chiaravalli, Davide;Palli, Gianluca;Melchiorri, Claudio
2025
Abstract
We present a programming-by-demonstration framework that allows users to simultaneously teach both motion and compliance behaviors to collaborative robots. The system integrates a wearable surface electromyography interface and real-time vibrotactile feedback into the kinesthetic teaching process, enabling intuitive point-by-point modulation of robot’s mechanical compliance. Unlike prior methods that focus solely on trajectory or symbolic control, our approach leverages unsupervised co-contraction estimation for continuous impedance shaping, without the need for explicit offline procedures or labeled data. To validate the method, we redesigned and conducted two contact-rich tasks—industrial wiring and a welding-like operation—demonstrated by ten subjects using a 7-degrees of freedom (DOF) collaborative manipulator. Results show that users could effectively program both trajectory and compliant interaction behaviors, highlighting the framework’s potential for intuitive and robust human–robot collaboration.| File | Dimensione | Formato | |
|---|---|---|---|
|
Programming_Robot_Interaction_Behavior_During_Kinesthetic_Teaching_Exploiting_sEMG-Based_Interfacing_and_Vibrotactile_Feedback.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale / Version Of Record
Licenza:
Creative commons
Dimensione
5.07 MB
Formato
Adobe PDF
|
5.07 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


