Jorge Silva – Robotics & Autonomous Systems

Robotics Researcher

Robotics & Autonomous Systems,
Royal Military Academy

Address

Avenue De La Renaissance 30, 1000 Brussels, Belgium

Contact Information

Call: –

Email: JorgeAndre.FreitasSilva@mil.be

Jorge Silva is an engineer with an excellent academic background in top-tier institutions (GPA: 5/5 & 18/20), a solid background in physics and over a year of hands-on research experience in robotics. His work has focused on the control of dynamical systems, computer vision, deep learning, and machine learning, and has extended across diverse domains, including retail, construction, biomedicine, and cargo transport. He is especially interested in applied research in control theory, robot perception, and multi-robot cooperation, particularly in the context of aerial robotics. Real-world viability is something he holds dear and strives for in his engineering projects, and is particularly motivated by the defense industry and the protection of democratic values. He brings adaptability, strong problem-solving skills, and a genuine passion for impactful engineering.

Publications

2025

V. N. Fernandez-Ayala, J. Silva, M. Guo, and D. V. Dimarogonas, “Robust visual servoing under human supervision for assembly tasks," European Journal of Control, p. 101312, 2025.
[BibTeX] [Abstract] [Download PDF] [DOI]

We propose a framework enabling mobile manipulators to reliably complete pick-and-place tasks for assembling structures from construction blocks. The picking uses an eye-in-hand visual servoing controller for object tracking with Control Barrier Functions (CBFs) to ensure fiducial markers in the blocks remain visible. An additional robot with an eye-to-hand setup ensures precise placement, critical for structural stability. We integrate human-in-the-loop capabilities for flexibility and fault correction and analyze robustness to camera pose errors, proposing adapted barrier functions to handle them. Lastly, experiments validate the framework on 6-DoF mobile arms.

@article{FERNANDEZAYALA2025101312,
title = {Robust visual servoing under human supervision for assembly tasks},
journal = {European Journal of Control},
pages = {101312},
year = {2025},
issn = {0947-3580},
doi = {https://doi.org/10.1016/j.ejcon.2025.101312},
url = {https://www.sciencedirect.com/science/article/pii/S0947358025001414},
author = {Victor Nan Fernandez-Ayala and Jorge Silva and Meng Guo and Dimos V. Dimarogonas},
keywords = {Visual servoing, Control Barrier Functions, Human-in-the-loop, Construction assembly, Object tracking},
abstract = {We propose a framework enabling mobile manipulators to reliably complete pick-and-place tasks for assembling structures from construction blocks. The picking uses an eye-in-hand visual servoing controller for object tracking with Control Barrier Functions (CBFs) to ensure fiducial markers in the blocks remain visible. An additional robot with an eye-to-hand setup ensures precise placement, critical for structural stability. We integrate human-in-the-loop capabilities for flexibility and fault correction and analyze robustness to camera pose errors, proposing adapted barrier functions to handle them. Lastly, experiments validate the framework on 6-DoF mobile arms.}
}