University of Catania DIEEI

Transcription

1 University of Catania DIEEI DIEEI: Summary Table Institute University of Catania Year of foundation Refererence person Prof. Giovanni Muscato Website Scientific Areas Robotic Applications Scientific Expertise Team size Senior researchers Mobile robotics, Artificial Intelligence Walking and climbing Robots, Agriculture, Industrial applications Path planning, Advanced control systems, Sensing, Man-Robot Interfaces

2 DIEEI put on the research table a Robotics Team based on 7 professors and assistant professors and a number of students, docs and post-docs that ranges around 30 to 40 high skilled people. This well driven group is involved in a number of international initiatives starting from the membership to the CLAWAR (CLimbing And WAalking Robots), a european network, born as a funded Excellence Network, but still operating now and that includes high level research bodies like CSIC (Spain) and RMA (Belgium). Main capabilities of this group are addressed Fig Example of robotics in agriculture along two main lines: the robotics mobility and the fusion of electronics and neural studies (Insectoids realization and study) where a number of different researches like machine intelligence, neural networks, brain study, neurology, but also genetic research are joined together to increase the capability to offer intelligent and adaptive behaviours to artificial beings. In the following we reported some of the realizations of the group. The robotics platform in Fig. 84 has been designed for a medium/large production. It is for spraying anti-parasitic to vineyards and is also able to operate in greenhouses. Unfortunately the SME that initially asked for this product was forced to close by the economic crisis effects and the system is waiting for a possible other entrepreneur. Study of Etna behavior (Fig. 85 and Fig. 86) is carried out by the Robotics group together with the INGV and using both terrestrial and aerial approach. ROBOVOLC has been one of the first, all terrain, systems; it proven to be able to overcome most of the ETNA terrain roughnesses and realize local and global analysis of the volcano conditions. Most of the control decisions are taken autonomously by the robot depending on the terrain characteristics sensed by the on board equipment and evaluated by the data coming by the dynamical inertial unit of the robot. Fig RobovolC Fig UAV for Etna studies 131

3 For a more quick and real time study of changing conditions, for a more effective analysis of the volcano gases and for a study from the sky of the terrain formations, DIEEI is developing an UAV able to bring significant sensing payloads. The flight is allowed (under the law conditions) by the peculiar condition of the aerial space around ETNA, forbidden to all civil flights, and by the substantial deserted conditions of the area. Fig Developments on insect intelligence The other prominent research line of Catania University is in a more fundamental research, aiming at understanding how to put intelligence in an artificial being. This line is less close to the applications: it is still a fundamental research activity. The Drosophila model, used for the studies, is a 150 Kneuron network. It has been shown that a so limited neural system is anyway able to manage and exhibit a surprising number of behaviors (Fig. 87 and Fig. 88). Learning, curiosity, decision making processes, realization of large experience database have been proven to be within the capabilities of such a brain neural model. All of these processes can be replicated, as has been demonstrated, on an electronic analog based on the well known CNN network. The realization of such a network in a FPGA chip is the ultimate goal when the knowledge of the Drosophila brain will be pushed to a satisfactory level. The research is in progress, in the frame of an international cooperation that includes some of the more prestigious European Institutions. 132

4 Fig Insect brain neural model Main results (papers and realizations of contact persons) P. Arena, L. Fortuna, G. Muscato, M. G. Xibilia, Neural Networks in Multidimensional Domains: fundamentals and new trends in modelling and control, Lecture Notes in Control and Information Sciences Vol. 234, Springer-Verlag, Berlin (Germany), G.S. Virk, G. Muscato, A. Semerano, M. Armada and H.A. Warren, The CLAWAR project on mobile robotic, Industrial Robot: An International Journal Vol.31, N. 2, pp , S. Guccione, G. Muscato, Control Strategies Computing architectures and Experimental Results of the Hybrid Robot Wheeleg, IEEE Robotics and Automation Magazine, (IEEE Piscataway, U.S.A.), Vol.10, N.4, pp.33-43, December L. Fortuna, G. Muscato and G. Nunnari, On the Bilinear Transformation of LQG- Balanced Realizations, Automatica, Vol. 31, No.2,pp , (Elsevier, U.K.), Febbraio S. Livatino, G. Muscato, S. Sessa, C.Koffel, C. Arena, A. Pennisi, D. Di Mauro, E. Malkondu, Depth-Enhanced Mobile Robot Teleguide based on Video Images, IEEE Robotic and Automation Magazine, Special issue on New Vistas and Challenges in Telerobotics, Vol15,N.4, pp.58-67, December 2008 (Digital Object Identifier /MRA ) G. Astuti, D. Longo, C. D. Melita, G. Muscato, A. Orlando, HIL tuning of UAV for exploration of risky environments, International Journal on Advanced Robotic Systems, Vol.5, N.4, (ISSN ), December

5 M. Branciforte, A. Meli, G. Muscato, D. Porto, ANN and Non-integer Order Modeling of ABS Solenoid Valves, IEEE Transactions on Control Systems Technology, Vol.19, No.3, May 2011, pp http://dx.doi.org/ /tcst G. Muscato, F. Bonaccorso, L. Cantelli, D. Longo and C.D. Melita, Volcanic environments: Robots for Exploration and Measurement, IEEE Robotics & Automation Magazine, Vol.19, No.1, March 2012, pp.40-49, DOI: /MRA S. Livatino, F. Banno, G. Muscato, 3D Integration of Robot Vision and Laser Data with Semi-Automatic Calibration in Augmented Reality Stereoscopic Visual Interface, IEEE Transactions on Industrial Informatics, vol.8, N.1, Feb. 2012, pp , DOI: /TII F. Bonaccorso, L. Cantelli, G. Muscato, An Arc Welding Robot Control for a Shaped Metal Deposition Plant: Modular Software Interface and Sensors, IEEE Transaction on Industrial Electronics, vol.58, N.8, Aug.2011,pp , S.Livatino, G.Muscato, F.Privitera, Stereo Viewing and Virtual Reality Technologies in Mobile Robot Teleguide, IEEE Transactions on Robotics Vol.25,No.6, December 2009 (DOI: /TRO ). L Patanè, S Hellbach, AF Krause, P Arena, V Dürr, An insect-inspired bionic sensor for tactile localization and material classification with state-dependent modulation, Frontiers in Neurorobotics 6, 8 P Arena, L Patané, A Vitanza, Autonomous learning of collaboration among robots, Neural Networks (IJCNN), The 2012 International Joint Conference on, 1-8 P Arena, L Patané, PS Termini, Modeling attentional loop in the insect Mushroom Bodies, Neural Networks (IJCNN), The 2012 International Joint Conference on, 1-7 F Karabiber, P Arena, L Fortuna, S De Fiore, G Vagliasindi, S Arik, Implementation of a moving target tracking algorithm using Eye-RIS Vision System on a mobile robot, Journal of Signal Processing Systems 64 (3), I Aleo, P Arena, L Patané, Incremental learning for visual classification using Neural Gas, Neural Networks (IJCNN), The 2010 International Joint Conference on,