Giuseppe Silano - Publications

Publications

Below is a list of my publications, including book chapters, journals and conference papers. I also reported my posters. Drop me an e-mail if you are looking for the preprint of some specific paper not available here.

Please see my Google Scholar profile for a full list of citations and co-authors.

Book Chapters

G. Silano and L. Iannelli, “CrazyS: a software-in-the-loop simulation platform for the Crazyflie 2.0 nano-quadcopter,” in “Robot Operating System (ROS): The Complete Reference (Volume 4),” A. Koubaa, Ed. , Springer International Publishing, March, 2019. In press.

@inbook{Silano2019ROSVolume4,
  author = {Silano, G. and Iannelli, L.},
  editor = {Koubaa, A.},
  title = {Robot Operating System (ROS): The Complete Reference (Volume 4)},
  chapter = {CrazyS: a software-in-the-loop simulation platform for the Crazyflie 2.0 nano-quadcopter},
  publisher = {Springer International Publishing},
  group = {book-chapters},
  year = {2019},
  month = mar,
  status = {In press},
  code = {http://github.com/gsilano/CrazyS}
}

This chapter proposes a typical use case dealing with the physical simulation of autonomous robots (specifically, quadrotors) and their interfacing through ROS (Robot Operating System). In particular, we propose CrazyS, an extension of the ROS package RotorS, aimed to modeling, developing and integrating the Crazyflie 2.0 nano-quadcopter in the physics based simulation environment Gazebo. Such simulation platform allows to understand quickly the behavior of the flight control system by comparing and evaluating different indoor and outdoor scenarios, with a details level quite close to reality. The proposed extension, running on Kinetic Kame ROS version but fully compatible with the Indigo Igloo one, expands the RotorS capabilities by considering the Crazyflie 2.0 physical model, its flight control system and the Crazyflie’s on-board IMU, as well. A simple case study has been considered in order to show how the package works and how the dynamical model interacts with the control architecture of the quadcopter. The contribution can be also considered as a reference guide for expanding the RotorS functionalities in the UAVs field, by facilitating the integration of new aircrafts. We released the software as open-source code, thus making it available for scientific and educational activities.

Conferences

P. Daponte, L. De Vito, L. Glielmo, L. Iannelli, D. Liuzza, F. Picariello, and G. Silano, “A review on the use of drones for precision agriculture,” in 2018 1st Workshop - Metrology for Agriculture and Foresty (MetroAgriFor), October, 2018, Ancona, Italy.

@inproceedings{Silano2018MetroAgriFor,
  author = {Daponte, P. and De Vito, L. and Glielmo, L. and Iannelli, L. and Liuzza, D. and Picariello, F. and Silano, G.},
  booktitle = {2018 1st Workshop - Metrology for Agriculture and Foresty (MetroAgriFor)},
  title = {A review on the use of drones for precision agriculture},
  year = {2018},
  group = {conferences},
  month = oct,
  note = {Ancona, Italy}
}

In recent years, there has been a strong activity in the so-called precision agriculture, particularly the monitoring aspect, not only to improve productivity, but also to meet demand of a growing population. At a large scale, precise monitoring of cultivated fields is a quite challenging task. Therefore, this paper aims to propose a survey on techniques, applied to precision agriculture monitoring, through the use of drones equipped with multispectral, thermal and visible cameras. For each application, the main limitations are highlighted and the parameters to be considered before to perform a flight are reported.

G. Silano, E. Aucone, and L. Iannelli, “CrazyS: A Software-In-The-Loop Platform for the Crazyflie 2.0 Nano-Quadcopter,” in 2018 26th Mediterranean Conference on Control and Automation (MED), pp. 352–357, June, 2018, Zadar, Croatia.

@inproceedings{Silano2018MED,
  author = {Silano, G. and Aucone, E. and Iannelli, L.},
  booktitle = {2018 26th Mediterranean Conference on Control and Automation (MED)},
  title = {CrazyS: A Software-In-The-Loop Platform for the Crazyflie 2.0 Nano-Quadcopter},
  year = {2018},
  pages = {352--357},
  group = {conferences},
  doi = {10.1109/MED.2018.8442759},
  issn = {2473-3504},
  month = jun,
  preprint = {publications/med18.pdf},
  link = {https://ieeexplore.ieee.org/document/8442759},
  code = {http://github.com/gsilano/CrazyS},
  note = {Zadar, Croatia}
}

In this paper we propose CrazyS, an extension of the ROS (Robot Operating System) package RotorS, aimed to modeling, developing and integrating the Crazyflie 2.0 nano-quadcopter in the physics based simulation environment Gazebo. Such simulation platform allows to understand quickly the behavior of the flight control system by comparing and evaluating different indoor and outdoor scenarios, with a details level quite close to reality. The proposed extension expands RotorS capabilities by considering the Crazyflie 2.0 physical model and its flight control system, as well. A simple case study  has been considered in order to show how the package works. The use of open-source software makes the platform available for scientific and educational activities.

G. Silano and L. Iannelli, “An educational simulation platform for GPS-denied unmanned Aerial Vehicles aimed to the detection and tracking of moving objects,” in 2016 IEEE Conference on Control Applications (CCA), pp. 1018–1023, September, 2016, Buenos Aires, Argentina.

@inproceedings{Silano2016CCA,
  author = {Silano, G. and Iannelli, L.},
  booktitle = {2016 IEEE Conference on Control Applications (CCA)},
  title = {An educational simulation platform for GPS-denied unmanned Aerial Vehicles aimed to the detection and tracking of moving objects},
  year = {2016},
  pages = {1018-1023},
  group = {conferences},
  doi = {10.1109/CCA.2016.7587947},
  month = sep,
  preprint = {publications/cca16.pdf},
  link = {https://ieeexplore.ieee.org/document/7587947},
  note = {Buenos Aires, Argentina}
}

The main motivation of this work is to show, for educational purposes, that the visual based object tracking problem can be illustrated through the simulation-in-the-loop approach: by using the MathWorks Virtual Reality Toolbox together with Matlab, it is possible to simulate the behavior of a drone in a 3D environment when detection and control algorithms are run. Matlab VR is used due to the familiarity that students have with. In this way the attention can be moved to the classifier, the references generator and the trajectory tracking control. Each block is decoupled and independent, so it can be easily replaced with others thus simplifying the development phase.

Journals

G. Silano, “MAT-Fly: an educational platform for simulating Unmanned Aerial Vehicles aimed to detect and track moving objects,” March, 2019. Working paper.

@article{Silano2019MATFly,
  author = {Silano, G.},
  title = {MAT-Fly: an educational platform for simulating Unmanned Aerial Vehicles aimed to detect and track moving objects},
  group = {journals},
  year = {2019},
  month = mar,
  status = {Working paper},
  doi = {10.13140/RG.2.2.14878.43849},
  preprint = {publications/MAT-Fly_ArxivV1.pdf},
  link = {https://arxiv.org/abs/1904.00378},
  code = {https://github.com/gsilano/MAT-Fly}
}

The main motivation of this work is to propose a simulation approach for a specific task within the UAV (Unmanned Aerial Vehicle) field, i.e., the visual detection and tracking of arbitrary moving objects. In particular, it is described MAT-Fly, a numerical simulation platform for multi-rotors aircrafts characterized by ease of use and control development. The platform is based on Matlab and the MathWorks Virtual Reality (VR) and Computer Vision System (CVS) toolboxes that work together to simulate the behavior of a drone in a 3D environment while tracking a car that moves along a non trivial path. The VR toolbox has been chosen due to the familiarity that students have with Matlab and because it allows to move the attention to the classifier, the tracker, the reference generator and the trajectory tracking control thanks to its simple structure. The overall architecture is quite modular so that each block can be easily replaced with others by simplifying the development phase and by allowing to add even more functionalities. The numerical simulator makes easy and quick to insert and to remove flight control system components, testing and comparing different plans, both for indoor and outdoor scenarios, when computer vision algorithms are in the loop. In an automatic way, the simulator is able to acquire frames from the virtual world, to search for one or more objects on which it has been trained during the learning phase, and to track the target position applying a trajectory control, addressing in that way the image-based visual servoing problems. Some simple testbeds have been presented in order to show the effectiveness and robustness of the approach as well as the platform works. We released the software as open-source, making it available for educational activities.

Posters

G. Silano and and L. Iannelli, “An educational simulation platform for Unmanned Aerial Vehicles aimed to detect and track moving objects,” in S.I.D.R.A. (Italian Society of Automatic Control), National Meeting, September, 2017, Milan, Italy.

@inproceedings{Silano2017AutomaticaIT,
  author = {Silano, G. and and L. Iannelli},
  booktitle = {S.I.D.R.A. (Italian Society of Automatic Control), National Meeting},
  title = {An educational simulation platform for Unmanned Aerial Vehicles aimed to detect and track moving objects},
  year = {2017},
  group = {posters},
  doi = {10.13140/RG.2.2.14878.43849},
  month = sep,
  preprint = {publications/sidra17.pdf},
  code = {http://github.com/gsilano/MAT-Fly},
  note = {Milan, Italy}
}

The main motivation of this work is to show, for educational purposes, that the visual based object tracking problem can be illustrated through the simulation-in-the-loop approach: by using the MathWorks Virtual Reality Toolbox together with Matlab, it is possible to simulate the behavior of a drone in a 3D environment when detection and control algorithms are run. Matlab VR is used due to the familiarity that students have with. In this way the attention can be moved to the classifier, the references generator and the trajectory tracking control. Each block is decoupled and independent, so it can be easily replaced with others thus simplifying the development phase.