Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios
This paper proposes a novel lightweight visual perception system with Incremental Learning (IL), tailored to child–robot interaction scenarios. Specifically, this encompasses both an action and emotion recognition module, with the former wrapped around an IL system, allowing novel actions to be easi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/9/4/86 |
| _version_ | 1827669347356639232 |
|---|---|
| author | Niki Efthymiou Panagiotis Paraskevas Filntisis Gerasimos Potamianos Petros Maragos |
| author_facet | Niki Efthymiou Panagiotis Paraskevas Filntisis Gerasimos Potamianos Petros Maragos |
| author_sort | Niki Efthymiou |
| collection | DOAJ |
| description | This paper proposes a novel lightweight visual perception system with Incremental Learning (IL), tailored to child–robot interaction scenarios. Specifically, this encompasses both an action and emotion recognition module, with the former wrapped around an IL system, allowing novel actions to be easily added. This IL system enables the tutor aspiring to use robotic agents in interaction scenarios to further customize the system according to children’s needs. We perform extensive evaluations of the developed modules, achieving state-of-the-art results on both the children’s action BabyRobot dataset and the children’s emotion EmoReact dataset. Finally, we demonstrate the robustness and effectiveness of the IL system for action recognition by conducting a thorough experimental analysis for various conditions and parameters. |
| first_indexed | 2024-03-10T03:59:05Z |
| format | Article |
| id | doaj.art-7eb7a9697dbf49b5b91a2c408ba307e8 |
| institution | Directory Open Access Journal |
| issn | 2227-7080 |
| language | English |
| last_indexed | 2024-03-10T03:59:05Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj.art-7eb7a9697dbf49b5b91a2c408ba307e82023-11-23T10:48:10ZengMDPI AGTechnologies2227-70802021-11-01948610.3390/technologies9040086Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction ScenariosNiki Efthymiou0Panagiotis Paraskevas Filntisis1Gerasimos Potamianos2Petros Maragos3School of Electrical and Computer Engineering, National Technical University of Athens, 15780 Zografou, GreeceSchool of Electrical and Computer Engineering, National Technical University of Athens, 15780 Zografou, GreeceDepartment of Electrical and Computer Engineering, University of Thessaly, 38221 Volos, GreeceSchool of Electrical and Computer Engineering, National Technical University of Athens, 15780 Zografou, GreeceThis paper proposes a novel lightweight visual perception system with Incremental Learning (IL), tailored to child–robot interaction scenarios. Specifically, this encompasses both an action and emotion recognition module, with the former wrapped around an IL system, allowing novel actions to be easily added. This IL system enables the tutor aspiring to use robotic agents in interaction scenarios to further customize the system according to children’s needs. We perform extensive evaluations of the developed modules, achieving state-of-the-art results on both the children’s action BabyRobot dataset and the children’s emotion EmoReact dataset. Finally, we demonstrate the robustness and effectiveness of the IL system for action recognition by conducting a thorough experimental analysis for various conditions and parameters.https://www.mdpi.com/2227-7080/9/4/86visual perceptionvisual learningincremental learningaction recognitionemotion recognitionchild–robot interaction |
| spellingShingle | Niki Efthymiou Panagiotis Paraskevas Filntisis Gerasimos Potamianos Petros Maragos Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios Technologies visual perception visual learning incremental learning action recognition emotion recognition child–robot interaction |
| title | Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios |
| title_full | Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios |
| title_fullStr | Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios |
| title_full_unstemmed | Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios |
| title_short | Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios |
| title_sort | visual robotic perception system with incremental learning for child robot interaction scenarios |
| topic | visual perception visual learning incremental learning action recognition emotion recognition child–robot interaction |
| url | https://www.mdpi.com/2227-7080/9/4/86 |
| work_keys_str_mv | AT nikiefthymiou visualroboticperceptionsystemwithincrementallearningforchildrobotinteractionscenarios AT panagiotisparaskevasfilntisis visualroboticperceptionsystemwithincrementallearningforchildrobotinteractionscenarios AT gerasimospotamianos visualroboticperceptionsystemwithincrementallearningforchildrobotinteractionscenarios AT petrosmaragos visualroboticperceptionsystemwithincrementallearningforchildrobotinteractionscenarios |