top of page
LAB
Research
We are looking to search for new machine vision algorithms for robot inspection. For that, we are looking to improve Systems Designs methods, Computer Vision techniques and Coverage Planning algorithms for better automated inspection, specifically in critical infrastructure.
Publications:
Enhancing Robotic Quality Inspection, 2022-2024
We are enhancing DL-based defect segmentation and viewpoints planning for Construction Sites.
​
Vision-based Surface-Damage Reconstruction, 2021
New surface reconstruction method using a combination of normal integration on multi-light images and monocular camera. We implement different Surface Reconstruction algorithms.
.png)
Score of Damage, 2021
We are developing a Superficial Score of Damage using damage-sensitive features in the mesa-scale in order to cluster surface damage.
We designed and developed MBSE methods for MoonRanger, the first micro rover to explore for water in the south pole of the moon.
Machine Learning Methods for clustering surface-damage detection, 2021
We compare different ML methods to detect and cluster surface-damge levels into a concrete
Terrain Adaptation of Hexapod Robot via CentralPattern Generator and Policy Gradient, 2020
We propose a solution that parameterizes a robot’s gait using a CentralPattern Generator (CPG). By performing policy gradient on CPG parameters in-stead of joint velocities and positions, we reduce the size of our action space tocontain strictly periodic behaviors.
On-line Technology organizational systems for Armed Forces, 2020
We designed a Army Simulation system able to organic a embedded technology in a clusters and distributed systems.
Design of the mechanical Ventilator to face COVID, 2020
I particiipated to a team of engineers and doctors to developed a low-cost, open-source alternative, now ready for rapid production.
A comparison of machine learning methods for predicting final vehicle destinations, 2019
Three machine learning models are tested and compared: Multi-Layer Perceptron (MLP), Support Vector Machine (SVM) and Recurrent Neural Network (RNN) that has a sequence-to-sequence structure with attention mechanism.
bottom of page