Abstract
The world's population is estimated to reach nine billion people by the year 2050, which indicates that agricultural productivity must increase sustainably. The mechanisation and automatisation of agricultural tasks is an essential step to face population growth. Ground robots have been developed along the last decade for several agricultural applications, being, the autonomous and safe navigation one of the hardest challenge in this development. Moving autonomously, a mobile platform involves different tasks, such as localisation, mapping, motion control, and path planning, a crucial step for autonomous operations. This article performs a survey of different applications for path planning techniques applied to various agricultural contexts. This paper analyses different agricultural applications and details about the employed path planning method. The conclusion indicates that path planning has been successfully applied to agrarian robots for field coverage and point-to-point navigation, being that coverage path planning is slightly more advanced in this field.

Abstract
Recently Shannon’s Entropy has been incorporated in nature inspired metaheuristics with good results. Depending on the problem, the Grey Wolf Optimization (GWO) algorithm may suffer from premature convergence. Here, an Entropy Grey Wolf Optimization (E-GWO) technique is proposed with the overall aim to improve the original GWO performance. The entropy is used to track the GWO swarm diversity, comparing the distance values between the Alpha in relation to the Beta and Delta wolves. The aim of the E-GWO variant is to improve convergence and prevent stagnation in local optima, since ideally restarting the swarm agents will prevent this from happening. Simulation results are presented showing that E-GWO restarting mechanism can achieve better results than the original GWO algorithm for some benchmark functions. © 2020, Springer Nature Switzerland AG.

Abstract
Simple and easy to use methods are of great practical demand in the design of Proportional, Integral, and Derivative (PID) controllers. Controller design criteria are to achieve a good set-point tracking and disturbance rejection with minimal actuator variation. Achieving satisfactory trade-offs between these performance criteria is not easily accomplished with classical tuning methods. A particle swarm optimization technique is proposed to design PID controllers. The design method minimizes a compromise cost function based on both the integral absolute error and control signal total variation criteria. The proposed technique is tested on an Arduino-based Temperature Control Laboratory (TCLab) and compared with the Grey Wolf Optimization algorithm. Both TCLab simulation and physical data show that satisfactory trade-offs between the performance and control effort are enabled with the proposed technique.

Abstract
Several approaches with interesting results have been proposed over the years for robot grasp planning. However, the industry suffers from the lack of an intuitive and reliable system able to automatically estimate grasp poses while also allowing the integration of grasp information from the accumulated knowledge of the end user. In the presented paper it is proposed a non-object-agnostic grasping pipeline motivated by picking use cases from the aerospace industry. The planning system extends the functionality of the simulated annealing optimization algorithm for allowing its application within an industrial use case. Therefore, this paper addresses the first step of the design of a reconfigurable and modular grasping pipeline. The key idea is the creation of an intuitive and functional grasping framework for being used by factory floor operators according to the task demands. This software pipeline is capable of generating grasp solutions in an offline phase, and later on, in the robot operation phase, can choose the best grasp pose by taking into consideration a set of heuristics that try to achieve a successful grasp while also requiring the least effort for the robotic arm. The results are presented in a simulated and a real factory environment, relying on a mobile platform developed for intralogistic tasks. With this architecture, new state-of-art methodologies can be integrated in the future for growing the grasping pipeline and make it more robust and applicable to a wider range of use cases.

Abstract
The development of robotic solutions in unstructured environments brings several challenges, mainly in developing safe and reliable navigation solutions. Agricultural environments are particularly unstructured and, therefore, challenging to the implementation of robotics. An example of this is the mountain vineyards, built-in steep slope hills, which are characterized by satellite signal blockage, terrain irregularities, harsh ground inclinations, and others. All of these factors impose the implementation of precise and reliable navigation algorithms, so that robots can operate safely. This work proposes the detection of semantic natural landmarks that are to be used in Simultaneous Localization and Mapping algorithms. Thus, Deep Learning models were trained and deployed to detect vine trunks. As significant contributions, we made available a novel vine trunk dataset, called VineSet, which was constituted by more than 9000 images and respective annotations for each trunk. VineSet was used to train state-of-the-art Single Shot Multibox Detector models. Additionally, we deployed these models in an Edge-AI fashion and achieve high frame rate execution. Finally, an assisted annotation tool was proposed to make the process of dataset building easier and improve models incrementally. The experiments show that our trained models can detect trunks with an Average Precision up to 84.16% and our assisted annotation tool facilitates the annotation process, even in other areas of agriculture, such as orchards and forests. Additional experiments were performed, where the impact of the amount of training data and the comparison between using Transfer Learning and training from scratch were evaluated. In these cases, some theoretical assumptions were verified.

Abstract
The dropout of university students has been a factor of concern for educational institutions, affecting various aspects such as the institution’s reputation and funding and rankings. For this reason, it is essential to identify which students are at risk. In this study, algorithms based on decision trees and random forests are proposed to solve these problems using real data from 331 students from the University of Trásos-Montes and Alto Douro. In this work with these learning algorithms together with the training strategies, we managed to obtain an 89% forecast of students who may abandon their studies based on the evaluations of both semesters related to the first year and personal data. © 2021, Springer Nature Switzerland AG.