T�tulo: Robotica de Campo no Australian Centre for Field Robotics

Palestrante:  Fabio Ramos (University of Sydney)

Resumo:

This talk will be divided into three parts: Firstly, I will introduce  the
concept of Field Robotics and describe some of the current  projects at the
Australian Centre for Field Robotics (ACFR) involving  robotics applications
in large-scale outdoor environments, in both  urban, aerial and underwater
domains. The second part of the talk  will present a joint work with Dieter
Fox from University of  Washington, on probabilistic models for data
association and multi- sensor object recognition. The methodology is developed
using  extensions of Conditional Random Fields to capture spatial and
temporal information. I will show how these models can be learnt to
seamlessly integrate local and neighbourhood information for optimum
association and classification. The third part will be focused on  mining
automation. The combination of geostatistics, new data fusion  engines and
autonomous machines such as haul trucks, shovels and  drills can significantly
improve the predictability and the  efficiency of the mining process. The
concept of an autonomous mine  will be explained as part of the recently
established Rio Tinto  Centre for Mining Automation at ACFR. 


Short Bio

Fabio Ramos received his B.E. and MSc. in Mechatronics Engineering at
University of Sao Paulo in 2000 and 2003 respectively. He has  completed his
PhD at the Australian Centre for Field Robotics in  2007. Currently, Fabio
Ramos is a Research Fellow at the University  of Sydney working on statistical
machine learning and applications in  robotics and mining. He has won the best
paper award in the IEEE/RSJ  International Conference on Intelligent Robots
and Systems (IROS),  2005 and is Associate Editor for the IEEE International
Conference on  Robotics and Automation (ICRA) and the Publication Chair for
Robotics  Science and Systems (RSS), 2008.