Towards Real-World Application of Robotic Groups Using Computational Intelligence

Gustav Pessin, University of São Paulo, São Carlos, Brazil

Abstract

This talk will address the four main issues involved in the creation of a robotic group to combat wildfires: (i) how to monitor and predict the fire behavior using wireless sensor networks? (ii) how to create an autonomous large vehicle capable of operating in the proposed domain? (iii) how to create an autonomous strategy of swarm formation and performance? (iv) how to improve localization using wireless networks information? There are many fields where a single robot is neither sufficient nor competent enough to fulfill a task. Tasks like cleaning nuclear residuals or dealing with chemical accidents, wildfire combat, hostile environment exploration, security and critical missions might be better accomplished using a swarm of robots. The use of robots instead of human beings may add mobility, flexibility and robustness. The creation of our swarm-robots system relies on the intrinsic characteristics of the chosen application and on its relationship with bio-inspired models, including swarm behavior and evolutionary computation combined with machine learning.

Bio

Gustavo Pessin is a PhD student in the Institute of Mathematics and Computer Science at the University of São Paulo. He obtained a M.S. in Computer Science in 2008 from the University of the Sinos Valley. At ICMC/USP, he has been working on several research projects related to robotics and machine learning techniques. His current research interests are Mobile Robotics, Computational Intelligence, Multi-Agent systems and Environmental Monitoring with WSN.