Ekaitz Jauregi

Learn More
Naive Bayes is a well-known and studied algorithm both in statistics and machine learning. Bayesian learning algorithms represent each concept with a single probabilistic summary. This paper presents a variant of the Naive Bayes method, in which the original training set is augmented in the following fashion: Leave-One-Out procedure is applied over the(More)
We describe a robot capable of composing and playing traditional Basque impromptu verses - bertsoak. The system, called Bertsobot, is able to construct improvised verses according to given constraints on rhyme and meter, and to perform it in public. Towards this end, several tools and applications have been developed and integrated in Bertsobot, including:(More)
The aim of the work presented here is to develop a door identification subsystem based on door handle recognition. The problem is stated as deciding whether a door handle is present or not in the images taken by the robot while navigating. And it is solved from a supervised classification point of view, combining Machine Learning segmentation with the Hough(More)
This paper proposes a novel approach to combine data frommultiple low-cost sensors to detect people in a mobile robot. Robust detection of people is a key capability required for robots working in environments with people. Several works have shown the benefits of fusing data from complementary sensors. The Kinect sensor provides a rich data set at a(More)
The work presented here proposes two different ROS packages to enrich the teleoperation of the robot NAO: speech-based teleoperation (in Basque) and gesture-based teleoperation together with arm control. These packages have been used and evaluated in a human mimicking experiment. The tools offered can serve as a base for many applications.
This paper proposes a novel approach to select the individual classi ers to take part in a Multiple-Classi er System. Individual classi er selection is a key step in the development of multi-classi ers. Several works have shown the bene ts of fusing complementary classi ers. Nevertheless, the selection of the base classi ers to be used is still an open(More)
The task of planning a collision-free trajectory from a start to a goal position is fundamental for an autonomous mobile robot. Although path planning has been extensively investigated since the beginning of robotics, there is no agreement on how to measure the performance of a motion algorithm. This paper presents a new approach to perform robot(More)