TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors
Empreu sempre aquest identificador per citar o enllaçar aquest ítem
http://hdl.handle.net/10045/110537
Títol: | TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors |
---|---|
Autors: | Garcia-Garcia, Alberto | Zapata-Impata, Brayan S. | Orts-Escolano, Sergio | Gil, Pablo | Garcia-Rodriguez, Jose |
Grups d'investigació o GITE: | Robótica y Visión Tridimensional (RoViT) | Automática, Robótica y Visión Artificial | Arquitecturas Inteligentes Aplicadas (AIA) |
Centre, Departament o Servei: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | Universidad de Alicante. Departamento de Física, Ingeniería de Sistemas y Teoría de la Señal | Universidad de Alicante. Departamento de Tecnología Informática y Computación |
Paraules clau: | Graph Neural Networks | Tactile Sensors | Grasping | Grasp Stability | Deep Learning | Robotics |
Àrees de coneixement: | Ciencia de la Computación e Inteligencia Artificial | Ingeniería de Sistemas y Automática | Arquitectura y Tecnología de Computadores |
Data de publicació: | 30-de setembre-2019 |
Editor: | IEEE |
Citació bibliogràfica: | A. Garcia-Garcia, B. S. Zapata-Impata, S. Orts-Escolano, P. Gil and J. Garcia-Rodriguez, "TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors," 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 2019, pp. 1-8, doi: 10.1109/IJCNN.2019.8851984 |
Resum: | Tactile sensors provide useful contact data during the interaction with an object which can be used to accurately learn to determine the stability of a grasp. Most of the works in the literature represented tactile readings as plain feature vectors or matrix-like tactile images, using them to train machine learning models. In this work, we explore an alternative way of exploiting tactile information to predict grasp stability by leveraging graph-like representations of tactile data, which preserve the actual spatial arrangement of the sensor's taxels and their locality. In experimentation, we trained a Graph Neural Network to binary classify grasps as stable or slippery ones. To train such network and prove its predictive capabilities for the problem at hand, we captured a novel dataset of ~ 5000 three-fingered grasps across 41 objects for training and 1000 grasps with 10 unknown objects for testing. Our experiments prove that this novel approach can be effectively used to predict grasp stability. |
Patrocinadors: | This work has been funded by the Spanish Government with Feder funds (TIN2016-76515-R and DPI2015-68087-R), by two grants for PhD studies (FPU15/04516 and BES-2016-07829), by regional projects (GV/2018/022 and GRE16-19) and by the European Commission (COMMANDIA SOE2/P1/F0638), action supported by Interreg-V Sudoe. |
URI: | http://hdl.handle.net/10045/110537 |
ISBN: | 978-1-7281-1985-4 | 978-1-7281-1986-1 |
ISSN: | 2161-4393 (Print) | 2161-4407 (Online) |
DOI: | 10.1109/IJCNN.2019.8851984 |
Idioma: | eng |
Tipus: | info:eu-repo/semantics/conferenceObject |
Drets: | © 2019 IEEE |
Revisió científica: | si |
Versió de l'editor: | https://doi.org/10.1109/IJCNN.2019.8851984 |
Apareix a la col·lecció: | INV - RoViT - Comunicaciones a Congresos, Conferencias, etc. INV - AUROVA - Comunicaciones a Congresos Internacionales INV - AIA - Comunicaciones a Congresos, Conferencias, etc. |
Arxius per aquest ítem:
Arxiu | Descripció | Tamany | Format | |
---|---|---|---|---|
Garcia-Garcia_etal_IJCNN-2019_final.pdf | Versión final (acceso restringido) | 4,51 MB | Adobe PDF | Obrir Sol·licitar una còpia |
Garcia-Garcia_etal_IJCNN-2019_preprint.pdf | Preprint (acceso abierto) | 7,09 MB | Adobe PDF | Obrir Vista prèvia |
Tots els documents dipositats a RUA estan protegits per drets d'autors. Alguns drets reservats.