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).
State-of-the-art Artificial Intelligence method for detecting that you is really you and not some intruder entering the code on your mobile phone.
This research line aims at designing adaptive controllers by using Echo State Networks (ESN) as a efficient data-driven method for training recurrent neural networks capable of controlling complex nonlinear plants, with a focus on oil and gas production platforms from Petrobras.
The resulting ESN-based controllers should learn inverse models of the controlled plant in an online fashion by interacting with the industrial plant and observing its dynamical behaviors.
In collaboration with supervised Master Student Jean P. Jordanou.
Well model. Figure by Jahanshahi et al. (2012).
Manifold connecting two oil wells and a riser. Figure by Jordanou.
Scheme of Adaptive ESN-based controller and nonlinear plant. Figure by Jordanou
