A Multi-task Learning Framework for Grasping-Position Detection and Few-Shot Classification

It is a big problem that a model of deep learning for a picking robot needs many labeled images. Operating costs of retraining a model becomes very expensive because the object shape of a product or a part often is changed in a factory. It is important to reduce the amount of labeled images required...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-03
Hauptverfasser:	Yokota, Yasuto, Suzuki, Kanata, Kanazawa, Yuzi, Takebayashi, Tomoyoshi
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Classification Feature extraction Grasping (robotics) Image classification Image detection Machine learning Object recognition Operating costs Picking Retraining Robots
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!