Complex and high-computational-cost algorithms are usually the state-of-the-art solution for autonomous driving cases in which non-holonomic robots must be controlled in scenarios with spatial restrictions and interaction with dynamic obstacles while fulfilling at all times safety, comfort, and legal requirements. These highly complex software solutions must cover the high variability of use cases that might appear in traffic conditions, especially when involving scenarios with dynamic obstacles. Reinforcement learning algorithms are seen as a powerful tool in autonomous driving scenarios since the complexity of the algorithm is automatically learned by trial and error with the help of simple reward functions. This paper proposes a methodology to properly define simple reward functions and come up automatically with a complex and successful autonomous driving policy. The proposed methodology has no motion planning module so that the computational power can be limited like in the reactive robotic paradigm. Reactions are learned based on the maximization of the cumulative reward obtained during the learning process. Since the motion is based on the cumulative reward, the proposed algorithm is not bound to any embedded model of the robot and is not being affected by uncertainties of these models or estimators, making it possible to generate trajectories with the consideration of non-holonomic constrains. This paper explains the proposed methodology and discusses the setup of experiments and the results for the validation of the methodology in scenarios with dynamic obstacles. A comparison between the reinforcement learning algorithm and state-of-the-art approaches is also carried out to highlight how the methodology proposed outperforms state-of-the-art algorithms.

Over the past couple of decades, the explosion of densely interconnected data has stimulated the research, development and adoption of graph database technologies. From early graph models to more recent native graph databases, the landscape of implementations has evolved to cover enterprise-ready requirements. Because of the interconnected nature of its data, the biomedical domain has been one of the early adopters of graph databases, enabling more natural representation models and better data integration workflows, exploration and analysis facilities. In this work, we survey the literature to explore the evolution, performance and how the most recent graph database solutions are applied in the biomedical domain, compiling a great variety of use cases. With this evidence, we conclude that the available graph database management systems are fit to support data-intensive, integrative applications, targeted at both basic research and exploratory tasks closer to the clinic.

The use of humanoid robots as assistants in therapy processes is not new. Several projects in the past several years have achieved promising results when combining human–robot interaction with standard techniques. Moreover, there are multiple screening systems for autism; one of the most used systems is the Quantitative Checklist for Autism in Toddlers (Q-CHAT-10), which includes ten questions to be answered by the parents or caregivers of a child. We present Q-CHAT-NAO, an observation-based autism screening system supported by a NAO robot. It includes the six questions of the Q-CHAT-10 that can be adapted to work in a robotic context; unlike the original system, it obtains information from the toddler instead of from an indirect source. The detection results obtained after applying machine learning models to the six questions in the Autistic Spectrum Disorder Screening Data for Toddlers dataset were almost equivalent to those of the original version with ten questions. These findings indicate that the Q-CHAT-NAO could be a screening option that would exploit all the benefits related to human-robot interaction.

Artificial intelligence and all its supporting tools, e.g. machine and deep learning in computational intelligence-based systems, are rebuilding our society (economy, education, life-style, etc.) and promising a new era for the social welfare state. In this paper we summarize recent advances in data science and artificial intelligence within the interplay between natural and artificial computation. A review of recent works published in the latter field and the state the art are summarized in a comprehensive and self-contained way to provide a baseline framework for the international community in artificial intelligence. Moreover, this paper aims to provide a complete analysis and some relevant discussions of the current trends and insights within several theoretical and application fields covered in the essay, from theoretical models in artificial intelligence and machine learning to the most prospective applications in robotics, neuroscience, brain computer interfaces, medicine and society, in general.

In vitro neuronal cultures embodied in a closed-loop control system have been used recently to study neuronal dynamics. This allows the development of neurons in a controlled environment with the purpose of exploring the computational capabilities of such biological neural networks. Due to the intrinsic properties of in vitro neuronal cultures and how the neuronal tissue grows in them, the ways in which signals are transmitted and generated within and throughout the culture can be difficult to characterize. The neural code is formed by patterns of spikes whose properties are in essence nonlinear and non-stationary. The usual approach for this characterization has been the use of the post-stimulus time histogram (PSTH). PSTH is calculated by counting the spikes detected in each neuronal culture electrode during some time windows after a stimulus in one of the electrodes. The objective is to find pairs of electrodes where stimulation in one of the pairs produces a response in the other but not in the rest of the electrodes in other pairs. The aim of this work is to explore possible ways of extracting relevant information from the global response to culture stimulus by studying the patterns of variation over time for the firing rate, estimated from inverse inter-spike intervals, in each electrode. Machine learning methods can then be applied to distinguish the electrode being stimulated from the whole culture response, in order to obtain a better characterization of the culture and its computational capabilities so it can be useful for robotic applications.