Abstract
The industry tends to increasingly automate as many processes as possible, and to make this possible, they often resort to the use of robotic arms. This paper presents the development of a proposal for a modular joint for robotic arms that allows: to obtain the best possible torque/weight ratio; to be controlled in speed and/or position; to communicate with other joints and external microcontrollers; to keep the cost as low as possible; and to be easily reconfigurable. The proposed prototype was validated with real results.

Abstract
Scheduling assumes a crucial importance in manufacturing systems, optimizing the allocation of operations to the right resources at the most appropriate time. Particularly in the Flexible Manufacturing System (FMS) topology, where the combination of possibilities for this association exponential increases, the scheduling task is even more critical. This paper presents a heuristic scheduling method based on genetic algorithm for a robotic-centric FMS. Real experiments show the effectiveness of the proposed algorithm, ensuring a reliable and optimized scheduling process. © 2018 by World Scientific Publishing Co. Pte. Ltd.

Abstract
The 4th industrial revolution promotes the automatic inspection of all products towards a zero-defect and high-quality manufacturing. In this context, collaborative robotics, where humans and machines share the same space, comprises a suitable approach that allows combining the accuracy of a robot and the ability and flexibility of a human. This paper describes an innovative approach that uses a collaborative robot to support the smart inspection and corrective actions for quality control systems in the manufacturing process, complemented by an intelligent system that learns and adapts its behavior according to the inspected parts. This intelligent system that implements the reinforcement learning algorithm makes the approach more robust once it can learn and be adapted to the trajectory. In the preliminary experiments, it was used a UR3 robot equipped with a Force-Torque sensor that was trained to perform a path regarding a product quality inspection task.

Abstract
The number of applications in which industrial robots share their working environment with people is increasing. Robots appropriate for such applications are equipped with safety systems according to ISO/TS 15066:2016 and are often referred to as collaborative robots (cobots). Due to the nature of human-robot collaboration, the working environment of cobots is subjected to unforeseeable modifications caused by people. Vision systems are often used to increase the adaptability of cobots, but they usually require knowledge of the objects to be manipulated. The application of machine learning techniques can increase the flexibility by enabling the control system of a cobot to continuously learn and adapt to unexpected changes in the working environment. In this paper we address this issue by investigating the use of Reinforcement Learning (RL) to control a cobot to perform pick-and-place tasks. We present the implementation of a control system that can adapt to changes in position and enables a cobot to grasp objects which were not part of the training. Our proposed system uses deep Q-learning to process color and depth images and generates an ?-greedy policy to define robot actions. The Q-values are estimated using Convolution Neural Networks (CNNs) based on pre-trained models for feature extraction. To reduce training time, we implement a simulation environment to first train the RL agent, then we apply the resulting system on a real cobot. System performance is compared when using the pre-trained CNN models ResNext, DenseNet, MobileNet, and MNASNet. Simulation and experimental results validate the proposed approach and show that our system reaches a grasping success rate of 89.9% when manipulating a never-seen object operating with the pre-trained CNN model MobileNet.

Abstract
Future power systems encourage the use of renewable energy resources, among them wind power is of great interest, but its power output is intermittent in nature which can affect the stability of the power system and increase the risk of blackouts. Therefore, a forecasting model of the wind speed is essential for the optimal operation of a power supply with an important share of wind energy conversion systems. In this paper, two wind speed forecasting models based on multiple meteorological measurements of wind speed and temperature are proposed and compared according to their mean squared error (MSE) value. The first model concerns the artificial intelligence based on neural network (ANN) where several network configurations are proposed to achieve the most suitable structure of the problem, while the other model concerned the Adaptive Neuro-Fuzzy Inference System (ANFIS). To enhance the results accuracy, the invalid input samples are filtered. According to the computational results of the two models, the ANFIS has delivered more accurate outputs characterized by a reduced mean squared error value compared to the ANN-based model.

Abstract
Motion control is an important task in several areas, such as robotics where the angular position and speed should be acquired, usually with encoders. For slow angular speeds, an error is introduced spoiling the measurement. In this paper there will be proposed two new methodologies, that when combined allow to increase the precision whereas reducing the error, even on transient velocities. The two methodologies Variable Acquisition Window and a Quadrature Phase Compensation are addressed and combined simultaneously. A real implementation of the proposed algorithms is performed on a real hardware, with a DC motor and a low resolution encoder based on hall effect. The results validate the proposed approach since the errors are reduced compared with the standard Quadrature Encoder Reading.