Sistema de interacción humano-robot para la enseñanza-aprendizaje de una tarea de ordenamiento de objetos mediante comunicación verbal y gestual

Translated title of the contribution: Human-robot interaction system for teaching-learning of an object sorting task by means of verbal and gestural communication

A Martinez, Sandra Esperanza Nope Rodríguez, Humberto Loaiza, Jose Hernando Mosquera-Delacruz, Gabriel Rodriguez, Juan David Jamioy-Cabrera

Research output: Contribution to journalArticlepeer-review

Abstract

A multimodal (gestures and voice) human-robot interaction system was developed that allows users to teach color-cube sorting tasks to a robot. The evaluation of the system was performed by seven users in a quantitative and qualitative way. In the quantitati-ve tests, a total of 63 verbal interactions, 252 gestural interactions, and 63 multimodal interactions were evaluated. The recognition rate of the interactions was 98.41% for voice commands, 81.35% for gestural, and 80.95% for multimodal. After learning, the robot was able to correctly perform the task of classifying cubes by color in 100%; being able to respond successfully to initial conditions (locations and number of cubes) not previously taught. The qualitative evaluation of the system was carried out to know the perception of the users, yielding consistent results with the recognition percentages, favoring verbal interaction over multimodal interaction.
Translated title of the contributionHuman-robot interaction system for teaching-learning of an object sorting task by means of verbal and gestural communication
Original languageSpanish
Article numbere-20613133
Pages (from-to)1-21
Number of pages21
JournalIngeniería y Competitividad
Volume25
Issue numberSupl
DOIs
StatePublished - 29 Nov 2023

Fingerprint

Dive into the research topics of 'Human-robot interaction system for teaching-learning of an object sorting task by means of verbal and gestural communication'. Together they form a unique fingerprint.

Cite this