Enhancing Human-Robot Interaction: Riemannian Classification and Clustering for Error Potential Detection and Error Occurrence Estimation - Archive ouverte HAL
Poster De Conférence Année : 2023

Enhancing Human-Robot Interaction: Riemannian Classification and Clustering for Error Potential Detection and Error Occurrence Estimation

Résumé

Our approach uses EEG signals to detect the occurrence of errors deliberately introduced during flexion and extension with an orthosis device, as well as to estimate the timing of these errors. It has been developed and tested on the IntEr-HRI competition dataset [Kueper et al., 2023].


Mots clés

EEG

Domaines

Neurosciences
Fichier principal
Vignette du fichier
14733-ChocolaTeam_final.pdf (219.81 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04832577 , version 1 (12-12-2024)

Identifiants

  • HAL Id : hal-04832577 , version 1

Citer

Mathias Rihet, Kalou Cabrera Castillo, Sébastien Scannella, Tresols Juan Jesus Torre, Frédéric Dehais, et al.. Enhancing Human-Robot Interaction: Riemannian Classification and Clustering for Error Potential Detection and Error Occurrence Estimation. IJCAI Inter-HRI competition, Aug 2023, Macao, France. ⟨hal-04832577⟩
0 Consultations
0 Téléchargements

Partager

More