TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors
| Autor: | Brayan S. Zapata-Impata, Sergio Orts-Escolano, Pablo Gil, Jose Garcia-Rodriguez, Alberto Garcia-Garcia |
|---|---|
| Přispěvatelé: | 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, Robótica y Visión Tridimensional (RoViT), Automática, Robótica y Visión Artificial, Arquitecturas Inteligentes Aplicadas (AIA) |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Grasping Computer science Machine Learning (stat.ML) 02 engineering and technology 01 natural sciences Machine Learning (cs.LG) Computer Science - Robotics Deep Learning Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Computer vision Graph Neural Networks Tactile Sensors business.industry Deep learning 010401 analytical chemistry GRASP 020206 networking & telecommunications Robotics Ciencia de la Computación e Inteligencia Artificial 0104 chemical sciences Grasp Stability Graph (abstract data type) Artificial intelligence business Robotics (cs.RO) Arquitectura y Tecnología de Computadores Tactile sensor Ingeniería de Sistemas y Automática |
| Zdroj: | RUA. Repositorio Institucional de la Universidad de Alicante Universidad de Alicante (UA) IJCNN |
| Popis: | 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. 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|