Multimodal 6D Detection of Industrial Pallets, in Real and Virtual Environments, with Applications in Industrial AMRs

José Lourenço, Gonçalo Arsénio, Luís Garrote, Urbano Nunes

2024

Abstract

In this work we propose a multimodal 6D pose estimation approach to detect pallets, to be applied in industrial environments. The method is designed for future integration with Autonomous Mobile Robots (AMRs) for enhanced warehouse automation. Using the DenseFusion framework as basis, the proposed approach fuses RGB and Depth data using multi-head self-attention mechanisms to improve robustness. To test the proposed methods, three datasets were developed: two virtual and one real-world indoor dataset, with varying degrees of occlusion and alignment challenges. Experimental results demonstrated that the approach achieved a high accuracy in occluded virtual scenarios and a promising result in real indoor scenarios, with increased performance on higher error thresholds. The obtained results show the potential of this system for use in AMRs to enhance the efficiency and safety of automated pallet handling in industrial settings in the future.

Paper Citation

in Harvard Style

Lourenço J., Arsénio G., Garrote L. and Nunes U. (2024). Multimodal 6D Detection of Industrial Pallets, in Real and Virtual Environments, with Applications in Industrial AMRs. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO; ISBN 978-989-758-717-7, SciTePress, pages 345-352. DOI: 10.5220/0013073300003822

in Bibtex Style

@conference{icinco24,
author={José Lourenço and Gonçalo Arsénio and Luís Garrote and Urbano Nunes},
title={Multimodal 6D Detection of Industrial Pallets, in Real and Virtual Environments, with Applications in Industrial AMRs},
booktitle={Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO},
year={2024},
pages={345-352},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013073300003822},
isbn={978-989-758-717-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO
TI - Multimodal 6D Detection of Industrial Pallets, in Real and Virtual Environments, with Applications in Industrial AMRs
SN - 978-989-758-717-7
AU - Lourenço J.
AU - Arsénio G.
AU - Garrote L.
AU - Nunes U.
PY - 2024
SP - 345
EP - 352
DO - 10.5220/0013073300003822
PB - SciTePress