Humanoid robot localization in a soccer field using Deep Learning

With the evolution of humanoid robotics and its increasing use in diverse environments and tasks, it is imperative that the robot can interact with the environment and, therefore, understand it accurately to execute decision making. In this work, we presented the process of collecting a new dataset...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrade, Gabriel de, Colombini, Esther
Format: Online
Language:Portuguese
Published: Universidade Estadual de Campinas 2019
Subjects:
Online Access:https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2900
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864359314775343104
author Andrade, Gabriel de
Colombini, Esther
author_facet Andrade, Gabriel de
Colombini, Esther
author_sort Andrade, Gabriel de
collection Portal de Eventos Científicos da UNICAMP
container_reference Revista dos Trabalhos de Iniciação Científica da UNICAMP; n. 27 (2019): Congresso de Iniciação Científica UNICAMP; 1-1
description With the evolution of humanoid robotics and its increasing use in diverse environments and tasks, it is imperative that the robot can interact with the environment and, therefore, understand it accurately to execute decision making. In this work, we presented the process of collecting a new dataset for simulated soccer scenes. We simulated the RoboCup Humanoid challenge and collected over 200k images that contain up to 4 classes of objects, depth estimation, and bounding boxes. We then trained a modified multiclass version of J-MOD2 to validate the dataset and provide the landmarks distances to a Monte Carlo localization algorithm in order to estimate the robot position on the field.
first_indexed 2025-10-08T13:58:56Z
format Online
id ojs-article-2900
institution Universidade Estadual de Campinas
issn 2596-1969
language por
last_indexed 2025-10-08T13:58:56Z
publishDate 2019
publisher Universidade Estadual de Campinas
record_format ojs
spelling ojs-article-29002025-09-26T14:39:16Z Humanoid robot localization in a soccer field using Deep Learning Andrade, Gabriel de Colombini, Esther Localization Robotics Deep learning With the evolution of humanoid robotics and its increasing use in diverse environments and tasks, it is imperative that the robot can interact with the environment and, therefore, understand it accurately to execute decision making. In this work, we presented the process of collecting a new dataset for simulated soccer scenes. We simulated the RoboCup Humanoid challenge and collected over 200k images that contain up to 4 classes of objects, depth estimation, and bounding boxes. We then trained a modified multiclass version of J-MOD2 to validate the dataset and provide the landmarks distances to a Monte Carlo localization algorithm in order to estimate the robot position on the field. Universidade Estadual de Campinas 2019-11-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Artigo de convidado application/pdf https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2900 10.20396/revpibic2720192900 Revista dos Trabalhos de Iniciação Científica da UNICAMP; n. 27 (2019): Congresso de Iniciação Científica UNICAMP; 1-1 2596-1969 por https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2900/2897 Copyright (c) 2019 Revista dos Trabalhos de Iniciação Científica da UNICAMP http://creativecommons.org/licenses/by/4.0
spellingShingle Andrade, Gabriel de
Colombini, Esther
Localization
Robotics
Deep learning
Humanoid robot localization in a soccer field using Deep Learning
title Humanoid robot localization in a soccer field using Deep Learning
title_full Humanoid robot localization in a soccer field using Deep Learning
title_fullStr Humanoid robot localization in a soccer field using Deep Learning
title_full_unstemmed Humanoid robot localization in a soccer field using Deep Learning
title_short Humanoid robot localization in a soccer field using Deep Learning
title_sort humanoid robot localization in a soccer field using deep learning
topic Localization
Robotics
Deep learning
url https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2900
work_keys_str_mv AT andradegabrielde humanoidrobotlocalizationinasoccerfieldusingdeeplearning
AT colombiniesther humanoidrobotlocalizationinasoccerfieldusingdeeplearning