Online feature extraction for the incremental learning of gestures in human-swarm interaction
We present a novel approach for the online learning of hand gestures in swarm robotic (multi-robot) systems. We address the problem of online feature learning by proposing Convolutional Max-Pooling (CMP), a simple feed-forward two-layer network derived from the deep hierarchical Max-Pooling Convolut...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833351947714822144 |
|---|---|
| author | Nagi J. Giusti A. Nagi F. Gambardella L.M. Di Caro G.A. |
| author2 | 25825455100 |
| author_facet | 25825455100 Nagi J. Giusti A. Nagi F. Gambardella L.M. Di Caro G.A. |
| author_sort | Nagi J. |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | We present a novel approach for the online learning of hand gestures in swarm robotic (multi-robot) systems. We address the problem of online feature learning by proposing Convolutional Max-Pooling (CMP), a simple feed-forward two-layer network derived from the deep hierarchical Max-Pooling Convolutional Neural Network (MPCNN). To learn and classify gestures in an online and incremental fashion, we employ a 2nd order online learning method, namely the Soft-Confidence Weighted (SCW) learning scheme. In order for all robots to collectively take part in the learning and recognition task and obtain a swarm-level classification, we build a distributed consensus by fusing the individual decision opinions of robots together with the individual weights generated from multiple classifiers. Accuracy, robustness, and scalability of obtained solutions have been verified through emulation experiments performed on a large data set of real data acquired by a networked swarm of robots. © 2014 IEEE. |
| format | Conference Paper |
| id | my.uniten.dspace-21867 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | my.uniten.dspace-218672023-05-16T10:45:47Z Online feature extraction for the incremental learning of gestures in human-swarm interaction Nagi J. Giusti A. Nagi F. Gambardella L.M. Di Caro G.A. 25825455100 23392613000 56272534200 35600356600 6603204674 We present a novel approach for the online learning of hand gestures in swarm robotic (multi-robot) systems. We address the problem of online feature learning by proposing Convolutional Max-Pooling (CMP), a simple feed-forward two-layer network derived from the deep hierarchical Max-Pooling Convolutional Neural Network (MPCNN). To learn and classify gestures in an online and incremental fashion, we employ a 2nd order online learning method, namely the Soft-Confidence Weighted (SCW) learning scheme. In order for all robots to collectively take part in the learning and recognition task and obtain a swarm-level classification, we build a distributed consensus by fusing the individual decision opinions of robots together with the individual weights generated from multiple classifiers. Accuracy, robustness, and scalability of obtained solutions have been verified through emulation experiments performed on a large data set of real data acquired by a networked swarm of robots. © 2014 IEEE. Final 2023-05-16T02:45:47Z 2023-05-16T02:45:47Z 2014 Conference Paper 10.1109/ICRA.2014.6907338 2-s2.0-84929191704 https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929191704&doi=10.1109%2fICRA.2014.6907338&partnerID=40&md5=039f82241da3af5cc500de59be7b2b94 https://irepository.uniten.edu.my/handle/123456789/21867 6907338 3331 3338 Institute of Electrical and Electronics Engineers Inc. Scopus |
| spellingShingle | Nagi J. Giusti A. Nagi F. Gambardella L.M. Di Caro G.A. Online feature extraction for the incremental learning of gestures in human-swarm interaction |
| title | Online feature extraction for the incremental learning of gestures in human-swarm interaction |
| title_full | Online feature extraction for the incremental learning of gestures in human-swarm interaction |
| title_fullStr | Online feature extraction for the incremental learning of gestures in human-swarm interaction |
| title_full_unstemmed | Online feature extraction for the incremental learning of gestures in human-swarm interaction |
| title_short | Online feature extraction for the incremental learning of gestures in human-swarm interaction |
| title_sort | online feature extraction for the incremental learning of gestures in human-swarm interaction |
| url_provider | http://dspace.uniten.edu.my/ |