Igor Rodriguez

Humanizing NAO robot teleoperation using ROS

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.

Undirected cyclic graph based multiclass pair-wise classifier

Supervised classification approaches try to classify correctly the new unlabelled examples based on a set of well-labelled samples. Nevertheless, some classification methods were formulated for binary classification problems and has difficulties for multi-class problems. Binarization strategies decompose the original multi-class dataset into multiple two-class subsets. For each new sub-problem a classifier is constructed. One-vs-One is a popular decomposition strategy that in each sub-problem discriminates the cases that belong to a pair of classes, ignoring the remaining ones. One of its drawbacks is that it creates a large number of classifiers, and some of them are irrelevant. In order to reduce the number of classifiers, in this paper we propose a new method called Decision Undirected Cyclic Graph. Instead of making the comparisons of all the pair of classes, each class is compared only with other two classes; evolutionary computation is used in the proposed approach in order to obtain suitable class pairing. In order to empirically show the performance of the proposed approach, a set of experiments over four popular Machine Learning algorithms are carried out, where our new method is compared with other well-known decomposition strategies of the literature obtaining promising results. HighlightsA new version of One-Vs-One is presented where the number of classifiers is reduced.Each class is compared only with other two classes.Evolutionary computation is used to obtain suitable class pairing.The proposed approach is compared with other state of the art methods over 4 different machine learning algorithms obtaining comparable results.

Singing minstrel robots, a means for improving social behaviors

Bertsolaritza, Basque improvised contest poetry, offers another sphere to develop robot body language and robot communication capabilities, that shares some similarities with theatrical performances. It is also a new area to work on social robotics. The work presented in this paper makes some steps forward in designing and implementing the set of behaviors the robots need to show in the stage to increase, on the one hand robot autonomy and on the other hand, credibility and sociability.

Machine Learning approach to dissimilarity computation: Iris matching

This paper presents a novel approach for iris dissimilarity computation based on Machine Learning paradigms and Computer Vision transformations. Based on the training dataset given by the MICHE II Challenge organizers, a set of classifiers has been constructed and tested, aiming at classifying a single image.

Emotional Poetry Generation

In this article we describe a new system for the automatic creation of poetry in Basque that not only generates novel poems, but also creates them conveying a certain attitude or state of mind. A poem is a text structured according to predefined formal rules, whose parts are semantically related and with an intended message, aiming to elicit an emotional response. The proposed system receives as an input the topic of the poem and the affective state (positive, neutral or negative) and tries to give as output a novel poem that: (1) satisfies formal constraints of rhyme and metric, (2) shows coherent content related to the given topic, and (3) expresses them through the predetermined mood. Although the presented system creates poems in Basque, it is highly modular and easily extendable to new languages.

Adaptive Emotional Chatting Behavior to Increase the Sociability of Robots

Emotion expression is one of the characteristics that make us social beings. It is one of the main forms, along with oral and written language, that gives us a glimpse into the inner mental state of another individual. One of the aims of social robotics is the effortless communication between humans and robots. To achieve this goal, robotic emotional expression is a key ability, as it offers a more natural way to interact in a human-robot environment. In this paper a system to express the emotional content of a spoken text is presented. Head and arms movements, along with eye LED lighting and voice intonation are combined to make a humanoid robot express the sadness-happiness emotion continuum. The robot is able to express the emotional meaning of texts in English, Spanish and Basque languages.

NAO Robot as Rehabilitation Assistant in a Kinect Controlled System

In this paper NAO robot is presented as a Home Rehabilitation assistant; Machine Learning is used to classify the data provided by a Kinect RGB-D sensor in order to obtain a Home Exercise Monitoring System which aims at helping physicians controlling patient at home rehabilitation.

Minstrel robots: Body language expression through applause evaluation

Currently humanoid robots become technically more capable of executing complex movements, showing human-like gestures, sometimes even facial expressions, and acting in general. While this lays the basis to make robot theater/enactments more and more interesting for the audience, another key-component is flexibility in the flow of an event to move on from simple pre-scripting. Here a sophisticated method is introduced relying on audio processing, clustering and machine learning techniques to evaluate audiences applauses, allowing the robot to infer self-evaluation about its actions. In a second step we use this information and a humanoid robots body language to alter the flow of the event and display a reaction for the audience.

Markov Text Generator for Basque Poetry

Poetry generation is a challenging field in the area of natural language processing. A poem is a text structured according to predefined formal rules and whose parts are semantically related. In this work we present a novel automated system to generate poetry in Basque language conditioned by non-local constraints. From a given corpus two Markov chains representing forward and backward 2-grams are built. From these Markov chains and a semantic model, a system able to generate poems conforming a given metric and following semantic cues has been designed. The user is prompted to input a theme for the poem and also a seed word to start the generating process. The system produces several poems in less than a minute, enough for using it in live events.

Supervised + Unsupervised Classification for Human Pose Estimation with RGB-D Images: A First Step Towards a Rehabilitation System

A system has been developed to detect postures and movements of people, using the skeleton information provided by the OpenNI library. A supervised learning approach has been used for generating static posture classifier models. In the case of movements, the focus has been done in clustering techniques. These models are included as part of the system software once generated, which reacts to postures and gestures made by any user. The automatic detection of postures is interesting for many applications, such as medical applications or intelligent interaction based on computer vision.