Abstract
Maintaining the quality control of scientific literature is one of the main characteristics of the peer review process. However, it depends on the peers' effectiveness in minimizing the intrinsic subjectivity to the process. Publishers try to achieve this through training and guides for reviewers. However, there is no consensus as to what the main criteria for a good review are, which results in poorly reasoned or vague reports that do not assist the editor in his decision nor the author in improvement of research. This project proposes a quality model for reviewing articles and a framework for their automatic classification through machine learning techniques. This proposal will be useful for: i) reviewers as a guideline for the preparation of the review report, editors as an indicator of the quality of the received revisions, and the authors as a model for self-evaluation of their research.

Abstract
To realize human-robot collaboration in manufacturing, industrial robots need to share an environment with humans and to work hand in hand. This introduces safety concerns but also provides the opportunity to take advantage of human-robot interactions to control the robot. The main objective of this work is to provide HRI without compromising safety issues in a realistic industrial context. In the paper, a region-based filtering and reasoning method for safety has been developed and integrated into a human-robot collaboration system. The proposed method has been successfully demonstrated keeping safety during the showcase evaluation of the European robotics challenges with a real mobile manipulator. © Springer International Publishing AG 2018.

Abstract
There are many open issues and challenges in the reinforcement learning field, such as handling high-dimensional environments. Function approximators, such as deep neural networks, have been successfully used in both single- and multi-agent environments with high dimensional state-spaces. The multi-agent learning paradigm faces even more problems, due to the effect of several agents learning simultaneously in the environment. One of its main concerns is how to learn mixed policies that prevent opponents from exploring them in competitive environments, achieving a Nash equilibrium. We propose an extension of several algorithms able to achieve Nash equilibriums in single-state games to the deep-learning paradigm. We compare their deep-learning and table-based implementations, and demonstrate how WPL is able to achieve an equilibrium strategy in a complex environment, where agents must find each other in an infinite-state game and play a modified version of the Rock Paper Scissors game. © Springer International Publishing AG 2018.

Abstract

Abstract
Dance movement is intrinsically connected to the rhythm of music and is a fundamental form of nonverbal communication present in daily human interactions. In order to enable robots to interact with humans in natural real-world environments through dance, these robots must be able to listen to music while robustly tracking the beat of continuous musical stimuli and simultaneously responding to human speech. In this paper, we propose the integration of a real-time beat tracking system with state recovery with different preprocessing solutions used in robot audition for its application to interactive dancing robots. The proposed system is assessed under different real-world acoustic conditions of increasing complexity, which consider multiple audio sources of different kinds, multiple noise sources of different natures, continuous musical and speech stimuli, and the effects of beat-synchronous ego-motion noise and of jittering in ego noise (EN). The overall results suggest improved beat tracking accuracy with lower reaction times to music transitions, while still enhancing automatic speech recognition (ASR) run in parallel in the most challenging conditions. These results corroborate the application of the proposed system for interactive dancing robots.

Abstract
Stochastic search algorithms are black-box optimizer of an objective function. They have recently gained a lot of attention in operations research, machine learning and policy search of robot motor skills due to their ease of use and their generality. However, when the task or objective function slightly changes, many stochastic search algorithms require complete re-leaming in order to adapt thesolution to the new objective function or the new context. As such, we consider the contextual stochastic search paradigm. Here, we want to find good parameter vectors for multiple related tasks, where each task is described by a continuous context vector. Hence, the objective function might change slightly for each parameter vector evaluation. In this paper, we investigate a contextual stochastic search algorithm known as Contextual Relative Entropy Policy Search (CREPS), an information-theoretic algorithm that can learn from multiple tasks simultaneously. We show the application of CREPS for simulated robotic tasks.