Embedded Files
About Me
About Me
Tiago Barros, PhD, is a research scientist at the Institute of Systems and Robotics, University of Coimbra, Portugal. His research focuses on 3D perception with LiDAR, machine learning, localization, and mapping, with applications in both agricultural and urban environments. He has developed methods for place recognition, SLAM, and sensor fusion, as well as multimodal perception systems that integrate LiDAR, multispectral, and thermal imagery. His work has been published in leading conferences and journals, including ITSC, IROS, RA-L, and Computers and Electronics in Agriculture.
His research interests lie at the intersection of robotics, 3D perception, and machine learning.
E-mail: tiagobarros@isr.uc.pt(NotCopy)
Publications
Publications
Journals
[4] T. Adão, J. Cerqueira, M. Adão, N. Silva, D. Pascoal, L. G. Magalhães, T. Barros, C. Premebida, U. J. Nunes, E. Peres, and R. Morais. Promore: A procedural modeler of virtual rural environments with artificial dataset generation capabilities for remote sensing contexts. IEEE Access, 13:47632–47652, 2025.
[3] R. Pereira, T. Barros, L. Garrote, A. Lopes, and U. J. Nunes. A Deep Learning-based Global and Segmentation-based Semantic Feature Fusion Approach for Indoor Scene Classification. Pattern Recognition Letters, 179:24–30,2024.
[2] T. Barros, L. Garrote, P. Conde, M. J. Coombes, Cunjia Liu, C. Premebida, and U.J. Nunes. PointNetPGAP-SLC: A 3D LiDAR-Based Place Recognition Approach With Segment-Level Consistency Training for Mobile Robots in Horticulture. IEEE Robotics and Automation Letters, 9(11):10471-10478,2024.
[1] T. Barros, P. Conde, G. Gonçalves, C. Premebida, M. Monteiro, CSS Ferreira, and U. J. Nunes. Multispectral vineyard segmentation: A Deep Learning Comparison Study. Computers and Electronics in Agriculture, 195:106782, 2022.
Conference Papers
[18] W. Cardoso, T. Barros, G. Gonçalves, and C. Premebida. "A Probabilistic Framework Applied to Multispectral Image Segmentation." In 2024 IEEE 3rd International Conference on Intelligent Reality (ICIR), pp. 1-2. IEEE, 2024. DOI: 10.1109/ICIR64558.2024.10976777
[17] M. Aleksandrov, K. Yordanova, R. Borges, Diogo Soares, T. Barros, and C. Premebida. "Safer and Trustworthier Navigation of Automated Vehicles." In 2025 25th International Conference on Control Systems and Computer Science (CSCS), pp. 183-189. IEEE, 2025. DOI: 10.1109/CSCS66924.2025.00035
[16] W. Cardoso, T. Barros, G. Gonçalves, C. Premebida, and U. J. Nunes. Multispectral Image Segmentation in Agriculture: Evaluating Deep Learning Models with Train-Test Split and Cross-Validation Strategies. In 2024 7th Iberian Robotics Conference (ROBOT), 2024. DOI: 10.1109/ROBOT61475.2024.10797395
[15] J. Jorge, T. Barros, C. Premebida, M. Aleksandrov, D. Goehring, and U. J. Nunes. Impact of 3D LiDAR Resolution in Graph-based SLAM Approaches: A Comparative Study. In 2024 7th Iberian Robotics Conference (ROBOT), 2024.
[14] T. Barros, C. Premebida, S. Aravecchia, C. Pradalier, and U. J. Nunes. SPV-SoAP3D: A Second-order Average Pooling Approach to enhance 3D Place Recognition in Horticultural Environments. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.
[13] T. Barros, L. Garrote, M. Aleksandrov, C. Premebida, and U. J. Nunes. TReR: A Lightweight Transformer Re-ranking Approach For 3D LiDAR Place Recognition. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023.
[12] N. Cunha, T. Barros, M. Reis, T. Marta, C. Premebida, and U. J. Nunes. Multispectral Image Segmentation in Agriculture: A Comprehensive Study on Fusion Approaches. In Robot 2023: Sixth Iberian Robotics Conference, 2023
[11] P. Conde, T. Barros, C. Premebida, and U. J. Nunes. ECE-based Deep Ensemble for Neural Network Calibration in Satellite Image Classification. In 2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2023.
[10] T. Barros, L. Garrote, R. Pereira, C. Premebida, and U. J. Nunes. Attdlnet: Attention-based Deep Network for 3D Lidar Place Recognition. In Robot 2022: Fifth Iberian Robotics Conference: Advances in Robotics, 2022.
[9] R. Pereira, L. Garrote, T. Barros, A. Lopes, and U. J. Nunes. A Deep Learning-based Indoor Scene Classification Approach Enhanced with Inter-object Distance Semantic Features. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
[8] J. NC Hayton, T. Barros, C. Premebida, M. J. Coombes, and U. J. Nunes. CNN-based Human Detection Using a 3D LiDAR onboard a UAV. In 2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2020.
[7] R. Pereira, T. Barros, L. Garrote, A. Lopes and U. J. Nunes, An Experimental Study of the Accuracy vs Inference Speed of RGB-D Object Recognition in Mobile Robotics. In 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2020.
[6] R. Pereira, N. Gonçalves, L. Garrote, T. Barros, A. Lopes and U. J. Nunes, Deep Learning based Global and Semantic Feature Fusion for Indoor Scene Classification. In 2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2020.
[5] L. Garrote, D. Temporão, S. Temporão, R. Pereira, T. Barros, and U. J. Nunes. Improving Local Motion Planning with a Reinforcement Learning Approach. In 2020 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2020.
[4] T. Barros, L. Garrote, R. Pereira, C. Premebida, and U. J. Nunes. Improving Localization by Learning Pole-like Landmarks using a Semi-supervised Approach. In Robot 2019: Fourth Iberian Robotics Conference: Advances in Robotics, 2020.
[3] L. Garrote, M. Torres, T. Barros, J. Perdiz, C. Premebida, and U. J. Nunes. Mobile robot localization with reinforcement learning map update decision aided by an absolute indoor positioning system. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.
[2] R. Pereira, L. Garrote, T. Barros, C. Carona, L. C. Bento, U. J. Nunes. Expressive Robotic Head for Human-Robot Interaction Studies. Mediterranean Conference on Medical and Biological Engineering and Computing, 2019.
[1] L. Garrote, T. Barros, R. Pereira, and U. J. Nunes. Absolute Indoor Positioning-aided Laser-based Particle Filter localization with a refinement stage. In IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society, 2019.
Preprints
[5] D. Mendonça, T. Barros, C.Premebida, and U. J. Nunes. "Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation for Zero-shot Generalization." arXiv preprint arXiv:2509.11772 2025. (Under Review)
[4] R. Pereira, L. Garrote, T. Barros, A. Lopes, and U. J. Nunes. Exploiting Object-based and Segmentation-based Semantic Features for Deep Learning-based Indoor Scene Classification. arXiv :2404.07739,2024.
[3] P. Conde, T. Barros, R. L. Lopes, C. Premebida, and U. J. Nunes. Approaching Test Time Augmentation in The Context of Uncertainty Calibration for Deep Neural Networks. arXiv:2304.05104, 2023
[2] T. Barros, L. Garrote, P. Conde, M. J. Coombes, C. Liu, C. Premebida, and U. J. Nunes. Orchnet: A Robust Global Feature Aggregation Approach for 3D LiDAR-based Place Recognition in Orchards. arXiv :2303.00477, 2023.
[1] T. Barros, R. Pereira, L. Garrote, C. Premebida, and U. J. Nunes. Place Recognition Survey: An Update on Deep Learning Approaches. arXiv :2106.10458, 2021.
Projects
Projects
Goal: The PharmaRobot project aims to improve hospital efficiency through an autonomous robot that delivers urgent medication quickly and accurately, reducing waiting times and minimizing human error. The proposed solution will enable more effective resource management, free up professionals for critical tasks, and ensure greater safety and quality in healthcare.
Role: Co-PI, Researcher
Execution period: 2025/03/1 - 2028/02/29
Goal: The main objective of the VESTA project is the development of vegetation management tools based on Earth Observation data and Artificial Intelligence (AI) for infrastructure management and maintenance operations, with a particular focus on the transportation (road) and energy (powerline) sectors.
Role: Associate Team Member
Reference: ESA Contract N.: 4000145501/24/I-LR
Execution period: 2024-10-01 - 2025-04-01
Goal: XPro is a bilateral project between ISR-UC and Universität Greifswald, funded by FCT (Portugal) and DAAD (Germany), aiming to tackle an important problem in engineering and robotics - probabilistic explainability of deep-models for robot-critical applications such as autonomous robot-perception, self-driving robot-vehicles, and decision making. XPro will focus on explainability by developing post-hoc techniques applied to existing pre-trained deep models applied to robot perception. In terms of case studies, XPro will explore two application domains, robotic perception and autonomous robotic-vehicles.
Role: Associate Team Member
Execution period: 2024-03-26 - 2026-03-25
Goal: : In PPS18, the objective is to develop an integrated warehouse management and on-line transport system, based on an intelligent AMR stacker-type platform, with natural navigation supported by a multisensory localization. The system will essentially consist of: 1)- Automated warehouse module: 2) Precise location module, optimized to operate in large warehouses; 3) Predictive maintenance module.
Role: Researcher
Execution period: 2022-10-01 - 2025-12-31
Multi-modal perception for long-term localization in human-centered robotics
Multi-modal perception for long-term localization in human-centered robotics
Goal: PhD grand financed by FCT
Role: Grant Beneficiary
Execution period: 2022-04-01 to 2025-03-31
Intelligent Robotic System for Digital Agriculture (GreenBotics)
Goal: GreenBotics project aims to make a significant step in Precision Agriculture by integrating sensing, field robotics, probabilistic machine learning and agriculture-science to develop a new soil-moisture monitoring system for crop plantations (namely Maize). The system is called Maize and Moisture Monitoring System (M3Sys). Based upon anovel multimodal spatio-temporal probabilistic inference framework, M3Sys will incorporate fundamental and applied techniques from machine learning, field robotics, drone andsatellite sensing, probability and sensor-fusion. Concisely, GreenBotics has the goal of increasing the precision and reliability of early anomalies detection and monitoring of Maize plantations by combining robotics, datasensor, ML, and agriculture expertise, both experimental and computational.Intelligent Robotic System for Digital Agriculture (GreenBotics)
Role: Researcher
Execution period: 2022-01-03 - 2025-04-02
Goal: GreenBotics project aims to make a significant step in Precision Agriculture by integrating sensing, field robotics, probabilistic machine learning and agriculture-science to develop a new soil-moisture monitoring system for crop plantations (namely Maize). The system is called Maize and Moisture Monitoring System (M3Sys). Based upon a novel multimodal spatio-temporal probabilistic inference framework, M3Sys will incorporate fundamental and applied techniques from machine learning, field robotics, drone and satellite sensing, probability and sensor-fusion. Concisely, GreenBotics has the goal of increasing the precision and reliability of early anomalies detection and monitoring of Maize plantations by combining robotics, data sensor, ML, and agriculture expertise, both experimental and computational.Intelligent Robotic System for Digital Agriculture (GreenBotics)
Role: Researcher
Reference: MIT-EXPL/TDI/0029/2019
Execution period: 2021-02-01 - 2022-01-31
MATIS - Materiais e Tecnologias Industriais Sustentável
Goal: This project aims at the development of sustainable industrial materials and technologies, namely multifunctional materials, innovative additive processes for mobility and health, advanced sensor systems for biomedical and environmental applications, development of sustainable processes for the valorization of agro-forestry waste, industrial process control, and the development of robotic functionalities in harsh environments.
Role: Researcher
Reference: Centro 2020 000014 MATIS 2020
Execution period: 2017-01-01 - 2021-05-31
Goal: The AGV developed within this project must have a low cost given that this is a very important factor for the industry market but, mainly, its offered functionalities must distinguish themselves by innovation and the suitability in the real world. Functionalities like bidirectional movement, being able to move in either direction, front or back, or lateral movement are functionalities considered to be very important for the industry world, but are just available at high cost, or not available at all in many AGV ranges. Besides we are proposing to develop an innovative global indoor localization system (Indoor GPS-LEDUS) which combines the use of communication technologies with Light Emitting Diode (LED) and ultrasound (US).
Role: Researcher
Reference: CENTRO-01-0247-FEDER-003503
Execution period: 2015-08-24 - 2019-02-28
Teaching
Teaching
Invited Assistant
Invited Assistant
I have been teaching the following courses:
Digital Systems Laboratory, undergraduate course at DEEC-UC (2025-2026)
Computer Programming, undergraduate course at DEEC-UC (2021-2022, 2022-2023)
Microprocessor Systems, undergraduate course at DEEC-UC (2021-2022, 2022-2023)
Talks, Workshops and Poster Sessions
Talks, Workshops and Poster Sessions
Dissemination of scientific results and outreach activities.
2025
"Semana dos Ramos", at the Department of Electrical and Computer Engineering, University of Coimbra, Coimbra, Portugal, Speaker.
ISR-UC OPEN LAB DAY - Health Edition, at the Institute of Systems and Robotics, Coimbra, Portugal, Member of the organizing team [Link].
Learning-based robotic perception in agriculture presented at the Colloquium on Agricultural robotics, Remote sensing and AI, University of Coimbra, Coimbra, Portugal, (Academic), Speaker and Organizer.
Large Language Models: A Practical Introduction presented at the Masterclass on AI & Machine Learning, Present Technologies, Coimbra, Portugal, (Industry), Speaker.
Presenting at the Masterclass on AI & Machine Learning
2024
Deep Learning-based Perception for Agricultural Robotics presented at the Workshop on Human-Centered Robotics (HCR) LAB, University of Coimbra, Portugal, (Academic), Speaker.
Deep Learning-based Multi-scale Observation for Precision Agriculture presented at the Workshop on MATHEMATICS FOR AGRICULTURE Trends and Challenges, University of Coimbra, Coimbra, Portugal, (Academic), Poster Presenter.
3D LiDAR-based Place Recognition in Horticultural Environments presented at the Open Research Day’s poster session, Institute of Systems and Robotics, Coimbra, Portugal, (Academic), Poster Presenter.
2023
Workshop on Introduction to C Programming, University of Coimbra, Portugal, (Academic), Speaker and Organizer.
Perception for Precision Agriculture and Autonomous Systems (Invited Talk), Freie Universität Berlin, Germany, (Academic), Speaker.
Multimodal Vineyard Segmentation using Deep Learning presented at the Dare2Change International Conference’s poster session, Porto, Portugal, (Academic), Poster Presenter. Honorable Mention
2022
Multi-spectral Remote Sensing for Viticulture presented at the workshop on “Gestão da vinha com recurso a Sistemas Inteligentes”, Escola Superior Agrária de Coimbra, Coimbra, Portugal, (Academic), Speaker and Organizer.
Multimodal Perception for Precision Agriculture presented at the Open Research Day’s poster session, Institute of Systems and Robotics, Coimbra, Portugal, (Academic), Poster Presenter.
Scientific Collaborations and International Engagement
Scientific Collaborations and International Engagement
I have actively collaborated with the following international and national institutions:
GeorgiaTech Lorraine (UMI2958 GT-CNRS, France): DRAEAM Lab, (Prof. Cédric Pradalier).
Loughborough University (United Kingdom): LUCAS Lab (Prof. Cunjia Liu).
Freie Universität Berlin (Germany): AutoNOMOS Lab (Prof. Daniel Göhring).
University of Minho, Portugal: ALGORITMI Research Centre/LASI (Dr. Telmo Adão).
University of Coimbra, Portugal: INESC (Prof. Gil Gonçalves).
Page updated
Google Sites
Report abuse