Available thesis A.Y. 2016 – 2017

Gustavo Stefanini Center available thesis A.Y.  2016 – 2017 :

  • Locomotion of snake-like robots: Modeling and Control,
  • Path planning for robot motion in complex environments,
  • Mobile robots exploration of unstructured and unknown environments,
  • Swarm robotics: Control and decision algorithms,
  • Industry 2.0: Integration of robots in collaborative industrial cells,
  • Long distance teleoperation of mobile robots with novel feedback modalities,
  • Computer vision techniques for place recognition, robot localization and structure reconstruction.

For further details, please contact cgsrobotics@gmail.com

07th May 2010, Anutei Annual Conference 2010, OTO MELARA Plant – Historical Pavillion, La Spezia

On May 7th, in OTO Melara historical pavilion was carried ANUTEI annual conference. ANUTEI is the NATIONAL ASSOCIATION of TECHNICAL OFFICIER of ITALIAN ARMY.
The 2010 conference was dedicated to new applications of robotics in the field of Home Land Security. It was an opportunity to make the state of the art and discuss lines of future research.
Eng. Villella, Gustavo Stefanini Center, presented a contribution entitled “Technological challenges in unmanned systems and new frontiers” and Eng. Cecchini teleoperated platform TRP1-B in the exhibition area dedicated to robotic prototypes.
The event was an opportunity to meet and compare with the industry world and potential end-users.

26th – 28th April 2010, “Distinguished lectures series in Field Robotics”, Prof. Steven Dubowsky, Director Field and Space Robotics Laboratory (FSRL) Massachusetts Institute of Technology (MIT), Cambridge, MA

Prof. Steven Dubowsky of MIT has been guest of Gustavo Stefanini Center from 26th to 28th April 2010 and he has held a series of seminars entitled “Distinguished Lectures in Field Robotics”.
The meetings were held in La Spezia and Pisa with the following schedule:

26th April 2010,Gustavo Stefanini Advanced Robotics Research Center Conference Room, La Spezia
15:00 – 18:00

The challenges of The Control of High Speed Rough Terrain Unmanned Robotic Vehicles
In recent years, substantial progress has been made in the research of unmanned robotic vehicles in rough terrains. For the past 15 years, the students and staff of the FSRL have been studying the planning and control of high-speed autonomous unmanned vehicles with support of NASA and the US Department of Defense. Initially, this work focused on autonomous vehicles moving slowly through highly unstructured environments, such as Mars Exploration Rovers. Algorithms were developed in which rovers would use understanding of its mechanics to proprioceptively estimate the shape and properties of the terrain. This type of sensing permits the vehicles to optimize their mobility and prevent entrapment. These results are then combined with long-distance vision to “project” the terrain knowledge into the far field. This work will be reviewed in this presentation.
More recent our research has focused on developing planning and control algorithms for high-speed rovers in rough terrain. The objective of this work is to avoid problems such as rollovers and sideslipping at high speeds due to unexpected obstacles and events. These problems are addressed in our work both analytically and experimentally. It is shown that high-speed conditions have inherent problems that make a complete solution very difficult, if not infeasible.

28th  April 2010,  Aula Magna Scuola Superiore Sant’Anna, Pise 10.00 – 13:00
“Digital Mechatronics: A New Robotics Design Paradigm with Example Applications: Mars Walking Explorers to Surgical Robots
Digital mechatronic devices approximate the motion of continuous mechanisms by using larger numbers of binary degrees-of-freedom. Digital mechatronic devices have excellent repeatability, are reliable, robust and simple to control. Muscle actuators made of elastomers, have limitations, however they are well suited for digital mechatronic devices. These actuators have unique properties such as they can produce large displacements with substantial forces. Furthermore, they are light and inexpensive.
In the work presented here, digital mechatronic systems were first considered for planetary exploration walking robots. This study has led to the development of surgical robots that can function effectively inside of MRI systems with important medical benefits.

Bio Prof. Steven Dubowsky
Dr. Dubowsky is a Professor in the Department of Mechanical Engineering and the Department of Aeronautics and Astronautics at the Massachusetts Institute of Technology, Cambridge, Massachusetts. He is the director of MIT Field and Space Robotics Laboratory (http://robots.mit.edu/).. He is the Principal Investigator of a number of research programs sponsored by organizations that include DARPA, NASA, The US Navy, The Center For the Integration of Medicine and Innovative Technology, industry, the Japanese Space Agency and the British government. The research of these programs focus on the design and control of robotic systems. Dr. Dubowsky has published over 300 technical papers and he is a Fellow of the ASME and of the IEEE.

Download the event brochure: DubowskyEventBrochure

 

21-27th May 2009, “Lectures on Robotics”, Gustavo Stefanini Research Centre, La Spezia

From 21/05 until 27/05/2009 a series of “Lectures on Robotics” have taken place at Gustavo Stefanini Research Center.
See below for complete program:

  • 21/05/2009: Robot global localization in minimalistic indoor environments: Theory and practice, Eng. Matteo Unetti
  • 22/05/2009: Robot Post Tracking with unknown feature association in indoor environments, Eng.Matteo Unetti
  • 27/05/2009: Implementation of HW control architecture for unmanned tracked vehicles, Eng. Rosario Merlino.

Download the event brochure: pose-tracking

17th April 2009, “Simulation with MDRS”, Gustavo Stefanini Center Conference Room, La Spezia

Microsoft® Robotics Developer Studio 2008 (MRDS) will become the new reference Windows-based framework to create robot applications and simulations for the Robotics Community. MRDS includes a set of useful tools for programming robot applications, as well as a high quality visual 3D-simulation environment including hardware acceleration.
This lecture provided an overview of the CGS experiences with the MRDS platform for robots and sensors simulation, with “live” demonstration of its usage and capabilities.  The lecture has been followed by a brief presentation  about the integration of realistic 3D physical object and robot models in the simulation environment enabling real-world physics simulation.

The lecture has been held in Gustavo Stefanini Center Conference Room, OTO Melara Plant.

Speakers: Eng. Emanuel Luchetti, Mr Gabriele Ascolese.

20th February – 13th March 2009 Lectures on Probabilistic Robotics

Eng. Paolo Villella held a series of lectures in Probabilistic Robotics.

All events has taken place in Gustavo Stefanini Center Conference Room, h. 10:00 – 13.00.

Lectures calendar and Abstracts.

20/02/09, Part 1: Introduction to Probabilistic Robotics
.Probabilities
.Bayes rule
.Bayes filter
A brief overview of the main problems faced in robotic navigation is provided, pointing out characteristics of the probabilistic approach. In the first part of the lesson, basics
in probability theory are given with a focus on bayesian interpretation of probability. The second part of the lesson is focused on Bayes rule and its application to some case
studies in robotics.

27/02/09, Part 2: Bayes Filter Implementations
.Gaussian filters
In the first part of the lesson, the Kalman filter is described, as an implementation of the Bayes filter using moments parameterization for linear systems. Next, the Kalman filter is extended to nonlinear problems (Extended Kalman Filter, EKF). The second part of the lesson is focused on the unscented Kalman filter and the information filter. Finally, real robotic applications of these filters are presented.

06/03/2009, Part 3: Bayes Filter Implementations
.Discrete filters
.Particle filters
This lesson discusses two nonparametric approaches for approximating posteriors over over continuous spaces with finitely many values. The first (histogram filter) assigns to each region a single cumulative probability. The second (particle filter) represents posteriors by finitely many samples. Finally, real robotic applications of these filters are presented.

13/03/09, Part 4: Probabilistic Motion Models and Probabilistic Sensor Models
I) PROBABILISTIC MOTION MODELS
II) PROBABILISTIC SENSOR MODELS
.Beam based
.Scan based
.Landmarks
The first part of the lesson focuses on mobile robot kinematics for robots operating in planar environments. Probabilistic motion models for skid-steering robots are derived, pointing out its robustness with respect to deterministic models. Finally, implementation of the resulting algorithms on real robots are discussed.
The second part of the lesson focuses on probabilistic perception, providing measurement models for range finders. In particular the use of scanning laser range finders is discussed. Finally, the use of grid based or feature based map is introduced, with some case studies.

11th – 14th June 2009, Sae Future 2009, SpeziaExpo, La Spezia (Italy)

From 11th to 14th June 2009, the Gustavo Stefanini Center took part in Universities section , the first edition of Future Sea, an exhibition dedicated to the technologies of the sea, which was attended by Italian and foreign companies and research centers . The Sea Future was an event inside of the Maritime Festival which was held in La Spezia from 11 to 16 June.

The Gustavo Stefanini Center was present with a booth where we exposed a robotic platform and a 3D laser scan, during the visits it was also possible to watch different videos about laboratory activities.

Download event brochure: Seafuture 2009 brochure

Just another WordPress site