Abstract
Deep learning models have as of late risen as popular function approximators for single-agent reinforcement learning challenges, by accurately estimating the value function of complex environments and being able to generalize to new unseen states. For multi-agent fields, agents must cope with the non-stationarity of the environment, due to the presence of other agents, and can take advantage of information sharing techniques for improved coordination. We propose an neural-based actor-critic algorithm, which learns communication protocols between agents and implicitly shares information during the learning phase. Large numbers of agents communicate with a self-learned protocol during distributed execution, and reliably learn complex strategies and protocols for partially observable multi-agent environments. © Springer Nature Switzerland AG 2019.

Abstract
This paper presents a new algorithm for a real-time obstacle avoidance for autonomous surface vehicles (ASV) that is capable of undertaking preemptive actions in complex and challenging scenarios. The algorithm is called adaptive velocity obstacle avoidance (AVOA) and takes into consideration the kinematic and dynamic constraints of autonomous vessels along with a protective zone concept to determine the safe crossing distance to obstacles. A configuration space that includes both the position and velocity of static or dynamic elements within the field-of-view of the ASV is supporting a particle swarm optimization procedure that minimizes the risk of harm and the deviation towards a predefined course while generating a navigation path with capabilities to prevent potential collisions. Extensive experiments demonstrate the ability of AVOA to select a velocity estimative for ASVs that originates a smoother, safer and, at least, two times more effective collision-free path when compared to existing techniques.

Abstract
For Programming teachers it is of utter most importance to understand the factors that impact on students' motivation to improve their ability to become good computer programmers. To understand a problem, to develop an algorithm for its solution, and to write the corresponding program is a challenging and arduous task, demanding time and self-confidence. In previous work we studied computer based technics to engage students in the learning activity; visualization, animation, automatic program assessment were some approaches that we combined. To support that work we studied carefully students' motivation and complemented that study with an inquiry to a group of students of Algorithm and Programming course of the first year of an Engineering degree. In this paper we show how Association Rules can be used to mine the data gathered in the inquiry to discover relationships among factors influencing extrinsic motivation.

Abstract
Distribution system operators (DSO) are currently moving towards active distribution grid management. One goal is the development of tools for operational planning of flexibility from distributed energy resources (DER) in order to solve potential (predicted) congestion and voltage problems. This work proposes an innovative flexibility management function based on stochastic and chance-constrained optimization that copes with forecast uncertainty from renewable energy sources (RES). Furthermore, the model allows the decision-maker to integrate its attitude towards risk by considering a trade-off between operating costs and system reliability. RES forecast uncertainty is modeled through spatial-temporal trajectories or ensembles. An AC-OPF linearization that approximates the actual behavior of the system is included, ensuring complete convexity of the problem. McCormick and big-M relaxation methods are compared to reformulate the chance-constrained optimization problem. The discussion and comparison of the proposed models is carried out through a case study based on actual generation data, where operating costs, system reliability and computer performance are evaluated.

Abstract
The number of electric vehicles (EVs) has been gradually increasing over the last decades. In order to eliminate the concerns related to charging demand in power systems, the appropriate integration of EVs to the grid is of great importance. Electric vehicle parking lots (EVPLs) offer a crucial occasion to manage the charging process of EVs. Further, EVs are capable of either charging from the grid or supplying power to the grid due to the vehicle-to-grid (V2G) features. Through an agent, namely an aggregator, EVPLs can participate in the electricity market and a considerable amount of profit can be obtained in terms of EVPLs, EV owners, and aggregators by energy selling. However, EV owners may not be willing to participate in this structure due to the concerns related to their comforts. In this context, a model in which EVPLs can bid for energy selling to the grid through an aggregator is proposed in this study. Additionally, the comfort violation of EV owners is taken into account. In order to validate the effectiveness of the devised model, various case studies are also performed.

Abstract
In this work, 3D printing is explored as a solution for fast prototyping of optical fiber sensors with applications in power transformers. Two different sensing structures were evaluated using finite element method (FEM) analysis and were fabricated using 3D printing. The printed structures are composed by acrylonitrile butadiene styrene (ABS), a common thermoplastic polymer used in 3D printing. Attaching a fiber Bragg grating (FBG) to each structure, frequency measurements were successfully obtained for values between 20 and 250 Hz.