In this paper we provide a general method to derive productform solutions for stochastic models. We take inspiration from the Reversed Compound Agent Theorem [14] and we provide a...
The development of high-performance libraries has become extraordinarily difficult due to multiple processor cores, vector instruction sets, and deep memory hierarchies. Often, t...
— We provide a general approach for learning robotic motor skills from human demonstration. To represent an observed movement, a non-linear differential equation is learned such ...
Peter Pastor, Heiko Hoffmann, Tamim Asfour, Stefan...
Abstract— This paper presents a novel method for sensorbased exploration of unknown environments by a general robotic system equipped with multiple sensors. The method is based o...
Structured prediction has become very important in recent years. A simple but notable class of structured prediction is one for sequences, so-called sequential labeling. For sequen...