Abstract
Robotic soccer simulation is a challenging area, where the development of new techniques is paramount to remain competitive. Robotic skill evolution has accelerated with recent developments in deep learning algorithms, leading to improvements in behavior number and complexity. Shooting a ball towards a defined target is one of the most basic yet indispensable skills in soccer. However, fast and accurate kicks pose several challenges. In order to reach that target, the skill is highly dependent on the ability of the agent to self-locate and self-orient, in order to better position itself before the kick. To tackle these issues, a 6D localization technique was devised. To optimize the kick behavior, two scenarios were proposed. In the first, the robot walks to the ball, stops, and then kicks. In the second, it kicks the ball while moving. We used state-of-the-art algorithms - Proximal Policy Optimization and Soft Actor Critic - to solve these complex problems and show their applicability in the context of RoboCup. Obtained results have shown very significant improvements over previously used behaviors by FC Portugal 3D team. The new kick in motion executes 5 times faster than the previous kick, and the new 6D pose estimator has an average error of just 6.3mm, a reduction of more than 97%.

Abstract
Data-driven decision support systems rely on increasing amounts of information that needs to be converted into actionable knowledge in business intelligence processes. The latter have been applied to diverse business areas, including governmental organizations, where they can be used effectively. The Portuguese Food and Economic Safety Authority (ASAE) is one example of such organizations. Over its years of operation, a rich dataset has been collected which can be used to improve their activity regarding prevention in the areas of food safety and economic enforcement. ASAE needs to inspect Economic Operators all over the country, and the efficient and effective generation of optimized and flexible inspection routes is a major concern. The focus of this paper is, thus, the generation of optimized inspection routes, which can then be flexibly adapted towards their operational accomplishment. Each Economic Operator is assigned an inspection utility - an indication of the risk it poses to public health and food safety, to business practices and intellectual property as well as to security and environment. Optimal inspection routes are then generated typically by seeking to maximize the utility gained from inspecting the chosen Economic Operators. The need of incorporating constraints such as Economic Operators' opening hours and multiple departure/arrival spots has led to model the problem as a Multi-Depot Periodic Vehicle Routing Problem with Time Windows. Exact and meta-heuristic methods were implemented to solve the problem and the Genetic Algorithm showed a high performance with realistic solutions to be used by ASAE inspectors. The hybrid approach that combined the Genetic Algorithm with the Hill Climbing also showed to be a good manner of enhancing the solution quality.

Abstract
Peer-reviewing is considered the main mechanism for quality control of scientific publications. The editors of journals and conferences assign submitted papers to reviewers, who review them. Therefore, inconsistencies between reviewer recommendations and reviewer comments are a problem that the editor needs to handle. However, few studies have explored whether it is possible to predict the reviewer recommendation from review comments based on NLP techniques. This study aims to predict reviewer recommendation of the scientific papers they review (accept or reject) and predict reviewers' final scores. We used a dataset composed of 2,313 review texts from two computer science conferences to test our approach, based on seven ML algorithms on regression and classification tasks and VADER application. SVM and MLP Classifier achieved the best performance in the classification task. In the regression task, the best performance was achieved by Nearest Neighbors. One of the most interesting results is the positive classification of most reviews by VADER: reviewers present constructively written reviews without highly negative comments land; therefore, VADER cannot detect reviews with a negative score.

Abstract
Gait disabilities empowered intensive research on the field of human-robot interaction to promote effective gait rehabilitation. Assist-as-needed strategies are becoming prominent, appealing to the users' participation in their rehabilitation therapy. This study proposes and assesses the biomechanical effects of an adaptive impedance control strategy that innovatively allows adaptability in interaction-based stiffness and gait trajectory towards a fully assist-as-needed therapy. By modulating the interaction-based stiffness per gait phase, we hypothesize that the strategy appeals to a symbiotic human-orthotic cooperation, augmenting the user's muscular activity. The interaction stiffness was estimated by modelling the human-orthosis interaction torque vs angle curve with a linear regression model. The strategy also allows for real-time trajectory adaptations at different gait phases to fulfil the users' needs. The biomechanical assessment of the impedance-controlled ankle orthosis involved eight healthy volunteers walking at 1.0 and 1.6 km/h. The results revealed a stronger muscular activation regarding the non-assisted leg for the gastrocnemius lateralis (increment ratio >= 1.0 for both gait speeds) and for the tibialis anterior muscle (increment ratio >= 1.0 for 1.6 km/h). The strategy guided users successfully on a healthy gait pattern while allowing deviations (median error < 5.0 degrees) given the users' intention weighted by interaction stiffness. Findings showed the relevance for adapting gait trajectory as users prefer higher trajectories as the speed increases. No significant temporal variations or neither knee angular compensations were observed (p value >= 0.11). Overall results support that this strategy may be applied for intensity-adapted gait training, allowing different human-robot compliant levels.

Abstract

Abstract