Athanasios S. Polydoros

Learn More
In certain cases analytical derivation of physics-based models of robots is difficult or even impossible. A potential workaround is the approximation of robot models from sensor data-streams employing machine learning approaches. In this paper, the inverse dynamics models are learned by employing a novel real-time deep learning algorithm. The algorithm(More)
A detailed analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM so the model equilibrates to a desired state. For this manner, four different types of Hebbian learning algorithms have been proposed in the(More)
A crucial part of a typical pattern recognition system is the extraction of the appropriate information that uniquely describes the patterns under processing. This information has the form of vectors and their contents are called features, which are constructed by specific extraction methods (Feature Extraction Methods FEMs). The length of the extracted(More)
Despite the large scientific interest on robot learning for object picking tasks [1]–[4], the research on object placing is too limited. Commonly, placing is simplistically considered as a trivial task, but real life manipulation problems indicate the exact opposite. A placing task can have different levels of complexity, ranging from the simplest tabletop(More)
Many robot learning algorithms depend on a model of the robot's forward dynamics for simulating potential trajectories and ultimately learning a required task. In this paper, we present a data-driven reservoir computing approach and apply it for learning forward dynamics models. Our proposed machine learning algorithm exploits the concepts of dynamic(More)
  • 1