Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About

About

Armando Sousa received his Ph.D. degrees in the area of Robotics at the University of Porto, Portugal in 2004.
He is currently an Auxiliary Professor in the same faculty and an integrated researcher in the INESCTEC (Institute for Systems and Computer Engineering of Porto - Technology and Science).
He received several international awards in robotic soccer under the RoboCup Federation (mainly in the small size league). He has also received the Pedagogical Excellence award of the UP in year 2015.
His main research interests include education, robotics, data fusion and vision systems. He has co-authored over 50 international peer-reviewed publications and participated in over 10 international projects in the areas of education and robotics.

Interest
Topics
Details

Details

003
Publications

2022

Localization and Mapping on Agriculture Based on Point-Feature Extraction and Semiplanes Segmentation From 3D LiDAR Data

Authors
Aguiar, AS; dos Santos, FN; Sobreira, H; Boaventura Cunha, J; Sousa, AJ;

Publication
FRONTIERS IN ROBOTICS AND AI

Abstract
Developing ground robots for agriculture is a demanding task. Robots should be capable of performing tasks like spraying, harvesting, or monitoring. However, the absence of structure in the agricultural scenes challenges the implementation of localization and mapping algorithms. Thus, the research and development of localization techniques are essential to boost agricultural robotics. To address this issue, we propose an algorithm called VineSLAM suitable for localization and mapping in agriculture. This approach uses both point- and semiplane-features extracted from 3D LiDAR data to map the environment and localize the robot using a novel Particle Filter that considers both feature modalities. The numeric stability of the algorithm was tested using simulated data. The proposed methodology proved to be suitable to localize a robot using only three orthogonal semiplanes. Moreover, the entire VineSLAM pipeline was compared against a state-of-the-art approach considering three real-world experiments in a woody-crop vineyard. Results show that our approach can localize the robot with precision even in long and symmetric vineyard corridors outperforming the state-of-the-art algorithm in this context.

2022

Using Simulation to Evaluate a Tube Perception Algorithm for Bin Picking

Authors
Leao, G; Costa, CM; Sousa, A; Reis, LP; Veiga, G;

Publication
ROBOTICS

Abstract
Bin picking is a challenging problem that involves using a robotic manipulator to remove, one-by-one, a set of objects randomly stacked in a container. In order to provide ground truth data for evaluating heuristic or machine learning perception systems, this paper proposes using simulation to create bin picking environments in which a procedural generation method builds entangled tubes that can have curvatures throughout their length. The output of the simulation is an annotated point cloud, generated by a virtual 3D depth camera, in which the tubes are assigned with unique colors. A general metric based on micro-recall is proposed to compare the accuracy of point cloud annotations with the ground truth. The synthetic data is representative of a high quality 3D scanner, given that the performance of a tube modeling system when given 640 simulated point clouds was similar to the results achieved with real sensor data. Therefore, simulation is a promising technique for the automated evaluation of solutions for bin picking tasks.

2022

Contactless Soil Moisture Mapping Using Inexpensive Frequency-Modulated Continuous Wave RADAR for Agricultural Purposes

Authors
Coutinho, RM; Sousa, A; Santos, F; Cunha, M;

Publication
APPLIED SCIENCES-BASEL

Abstract
Soil Moisture (SM) is one of the most critical factors for a crop’s growth, yield, and quality. Although Ground-Penetrating RADAR (GPR) is commonly used in satelite observation to analyze soil moisture, it is not cost-effective for agricultural applications. Automotive RADAR uses the concept of Frequency-Modulated Continuous Wave (FMCW) and is more competitive in terms of price. This paper evaluates the viability of using a cost-effective RADAR as a substitute for GPR for soil moisture content estimation. The research consisted of four experiments, and the results show that the RADAR’s output signal and the soil moisture sensor SEN0193 have a high correlation with values as high as 0.93 when the SM is below 15%. Such results show that the tested sensor (and its cost-effective working principle) are able to determine soil water content (with certain limitations) in a non-intrusive, proximal sensing manner.

2022

Tree Trunks Cross-Platform Detection Using Deep Learning Strategies for Forestry Operations

Authors
da Silva, DQ; dos Santos, FN; Filipe, V; de Sousa, AJM;

Publication
ROBOT 2022: Fifth Iberian Robotics Conference - Advances in Robotics, Volume 1, Zaragoza, Spain, 23-25 November 2022

Abstract

2022

Edge AI-Based Tree Trunk Detection for Forestry Monitoring Robotics

Authors
da Silva, DQ; dos Santos, FN; Filipe, V; Sousa, AJ; Oliveira, PM;

Publication
ROBOTICS

Abstract
Object identification, such as tree trunk detection, is fundamental for forest robotics. Intelligent vision systems are of paramount importance in order to improve robotic perception, thus enhancing the autonomy of forest robots. To that purpose, this paper presents three contributions: an open dataset of 5325 annotated forest images; a tree trunk detection Edge AI benchmark between 13 deep learning models evaluated on four edge-devices (CPU, TPU, GPU and VPU); and a tree trunk mapping experiment using an OAK-D as a sensing device. The results showed that YOLOR was the most reliable trunk detector, achieving a maximum F1 score around 90% while maintaining high scores for different confidence levels; in terms of inference time, YOLOv4 Tiny was the fastest model, attaining 1.93 ms on the GPU. YOLOv7 Tiny presented the best trade-off between detection accuracy and speed, with average inference times under 4 ms on the GPU considering different input resolutions and at the same time achieving an F1 score similar to YOLOR. This work will enable the development of advanced artificial vision systems for robotics in forestry monitoring operations.

Supervised
thesis

2021

Robot navigation in vineyards based on the visual vanish point concept

Author
José Maria Queirós Rodrigues Sarmento

Institution
UP-FEUP

2021

Tactode programming for robotics and other targets

Author
César Alexandre da Costa Pinho

Institution
UP-FEUP

2021

ChemLab - Remote robotic Laboratory for teaching Chemistry

Author
Rui Manuel Pereira Coutinho

Institution
UP-FEUP

2021

Blue Energy Harvesting of Ocean Waves: Optimizing Triboelectric Nanogenerators to Sea States in Integrated Experimental and Multiphysics Modelling

Author
Isabel Pinto Gonçalves

Institution
UM

2021

Definition of a conceptual model to asses the environmental sustainability of parcel delivery

Author
Vasco Silva

Institution
IES_Outra