Our paper, resulting from work of Master student Gustavo Claudio Karl Couto, entitled
"Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments" has shown very interesting results:
Both the intermediate mid-level input BEV representation and the control policy are learned as the agent navigates in an urban town (click for more videos from playlist).
I am Eric A. Antonelo, professor of Artificial Intelligence in the Department of Automation and Systems at Federal University of Santa Catarina since 2020 (more info here), and a computer scientist holding a Master degree in Computer Systems Engineering with a major in Intelligent Systems from Halmstad University, Sweden (Master thesis here) and a PhD degree in Computer Science from Ghent University, Belgium (PhD thesis here).
In my thesis, I proposed, designed and implemented reservoir computing architectures (RNNs) to model several intelligent capabilities in mobile robotics such as navigation and robot localization through learning and embedding dynamical systems from the robot environment data.
In 2016, I joined SnT at University of Luxembourg as a Research Associate to work on an industrial research PPP project with a private company for fraud detection on big datasets of energy distribution networks using machine learning techniques (RNNs and importance weighted predictive models).
As a post-doc from 2012 to 2016, I also taught topics on artificial intellingence for undergraduate and graduate students from Federal University of Santa Catarina (UFSC), such as Logic, Bayesian networks, Regression and Classification Methods (Logistic regression, Neural Networks, Decision trees) and Bayesian learning.
I have research and development experience on artificial intelligence, specially on machine learning methods such as neural networks and support vector machines for regression and classification; and on reinforcement learning in robotics. In addition, I worked on multi-variate data mining with chemical process data during a consulting project.
I have also experience on web development as software architect through implementing two vertical search engines:
See my gate.io or Research for more information.
I made available some code for machine learning (in Julia and in Python) when I started learning the Julia programming language.
I currently live in Florianópolis, Brazil.
In 2019, I lived in Maringá, Brazil.
From 2017 to 2019, I lived in Luxembourg.
From 2012 to 2016, I lived in Florianópolis, Brazil.
From 2007 to 2011, I lived in Ghent, Belgium.
From 2004 to Jan 2006, I lived in Halmstad, Sweden.
From 1998 to 2003, I lived in Maringá, Brazil.
Check my CV or my LinkedIn profile for more information.