Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to converge. This makes it difficult to be applied to re...
: This paper presents a Lab. implementation of a computer vision using fuzzy models for pattern recognition for the detection of boundaries in images obtained through a camera inst...
Adriano Breunig, Haroldo R. de Azevedo, Edilberto ...
Abstract. In this paper we present some preliminary results concerning a realtime visualisation system for densely populated urban environments. In order to be able to render the l...
Traditional offline program specialization relies on staging of a computation into two levels, static and dynamic. We present a generalization thereof where the static input data o...
The capability of perceiving the environment is crucial for advancing the level of autonomy and sophistication of (semi)autonomous robotic systems and determines the complexity of ...