Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots

In environments like the RoboCup Middle Size League (MSL), precise and rapid localisation of robots is crucial for effective autonomous interaction. This study addresses the limitations of conventional localisation approaches—often based on single-camera systems or sensors such as LiDAR (Light Detec...

Full description

Saved in:
Bibliographic Details
Main Authors: Carolina Coelho Lopes, António Ribeiro, Tiago Ribeiro, Gil Lopes, A. Fernando Ribeiro
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:AI
Subjects:
Online Access:https://www.mdpi.com/2673-2688/6/2/27
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849723344708960256
author Carolina Coelho Lopes
António Ribeiro
Tiago Ribeiro
Gil Lopes
A. Fernando Ribeiro
author_facet Carolina Coelho Lopes
António Ribeiro
Tiago Ribeiro
Gil Lopes
A. Fernando Ribeiro
author_sort Carolina Coelho Lopes
collection DOAJ
description In environments like the RoboCup Middle Size League (MSL), precise and rapid localisation of robots is crucial for effective autonomous interaction. This study addresses the limitations of conventional localisation approaches—often based on single-camera systems or sensors such as LiDAR (Light Detection and Ranging) and infrared—by developing a robust Artificial Intelligence (AI)-based multi-camera system solution. This method uses multiple neural networks, breaking down the problem while taking advantage of both classification and regression methods. The solution includes a classification neural network to detect field markers, such as line intersections, and two regression neural networks: one for calculating the position of the markers, and another for determining the robot’s position in real-time. It takes advantage of both approaches while maintaining the desired performance, accuracy, and robustness, simplifying the training process and adapting it to different scenarios. Designed specifically to meet MSL robotics’s high-speed demands and precision requirements, the system employs data augmentation techniques to ensure resilience against lighting, angles, and position variations. The results show that this optimised approach improves spatial awareness and accuracy, promising robot football advancements. Beyond MSL applications, this method has the potential for broader real-world uses that require dependable, real-time localisation in dynamic settings.
format Article
id doaj-art-e6b204e009e14f67b3074ffcc7b698cd
institution DOAJ
issn 2673-2688
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series AI
spelling doaj-art-e6b204e009e14f67b3074ffcc7b698cd2025-08-20T03:11:03ZengMDPI AGAI2673-26882025-02-01622710.3390/ai6020027Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous RobotsCarolina Coelho Lopes0António Ribeiro1Tiago Ribeiro2Gil Lopes3A. Fernando Ribeiro4Industrial Electronics Department, University of Minho, 4800-058 Guimarães, PortugalIndustrial Electronics Department, University of Minho, 4800-058 Guimarães, PortugalIndustrial Electronics Department, ALGORITMI Centre, 4800-058 Guimarães, PortugalLIACC & ISEP, Polytechnic Institute of Porto, 4249-015 Porto, PortugalIndustrial Electronics Department, ALGORITMI Centre, 4800-058 Guimarães, PortugalIn environments like the RoboCup Middle Size League (MSL), precise and rapid localisation of robots is crucial for effective autonomous interaction. This study addresses the limitations of conventional localisation approaches—often based on single-camera systems or sensors such as LiDAR (Light Detection and Ranging) and infrared—by developing a robust Artificial Intelligence (AI)-based multi-camera system solution. This method uses multiple neural networks, breaking down the problem while taking advantage of both classification and regression methods. The solution includes a classification neural network to detect field markers, such as line intersections, and two regression neural networks: one for calculating the position of the markers, and another for determining the robot’s position in real-time. It takes advantage of both approaches while maintaining the desired performance, accuracy, and robustness, simplifying the training process and adapting it to different scenarios. Designed specifically to meet MSL robotics’s high-speed demands and precision requirements, the system employs data augmentation techniques to ensure resilience against lighting, angles, and position variations. The results show that this optimised approach improves spatial awareness and accuracy, promising robot football advancements. Beyond MSL applications, this method has the potential for broader real-world uses that require dependable, real-time localisation in dynamic settings.https://www.mdpi.com/2673-2688/6/2/27neural networksclassificationregressionmulti-camera localisationartificial intelligencemarker-based positioning
spellingShingle Carolina Coelho Lopes
António Ribeiro
Tiago Ribeiro
Gil Lopes
A. Fernando Ribeiro
Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots
AI
neural networks
classification
regression
multi-camera localisation
artificial intelligence
marker-based positioning
title Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots
title_full Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots
title_fullStr Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots
title_full_unstemmed Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots
title_short Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots
title_sort multi neural network localisation system with regression and classification on football autonomous robots
topic neural networks
classification
regression
multi-camera localisation
artificial intelligence
marker-based positioning
url https://www.mdpi.com/2673-2688/6/2/27
work_keys_str_mv AT carolinacoelholopes multineuralnetworklocalisationsystemwithregressionandclassificationonfootballautonomousrobots
AT antonioribeiro multineuralnetworklocalisationsystemwithregressionandclassificationonfootballautonomousrobots
AT tiagoribeiro multineuralnetworklocalisationsystemwithregressionandclassificationonfootballautonomousrobots
AT gillopes multineuralnetworklocalisationsystemwithregressionandclassificationonfootballautonomousrobots
AT afernandoribeiro multineuralnetworklocalisationsystemwithregressionandclassificationonfootballautonomousrobots