In this study, a semantic segmentation network is presented to develop an indoor navigation system for a mobile robot. Semantic segmentation can be applied by adopting different techniques, such as a convolutional neural network (CNN). However, in the present work, a residual neural network is implemented by engaging in ResNet-18 transfer learning to distinguish between the floor, which is the navigation free space, and the walls, which are the obstacles. After the learning process, the semantic segmentation floor mask is used to implement indoor navigation and motion calculations for the autonomous mobile robot. This motion calculations are based on how much the estimated path differs from the center vertical line. The highest point is used to move the motors toward that direction. In this way, the robot can move in a real scenario by avoiding different obstacles. Finally, the results are collected by analyzing the motor duty cycle and the neural network execution time to review the robot’s performance. Moreover, a different net comparison is made to determine other architectures’ reaction times and accuracy values.

Air jet impingement systems have proven to be a very efficient way of heat transfer in single phase flows, which has allowed them to be applied in several industries. However, the complexity of the physical phenomena that take place in the cooling or heating processes makes the task of designing and sizing a system of this type very difficult. The objective of this work is to develop a methodology for the optimization of the impingement plate for electronic components cooling systems. The component chosen to exemplify this work is an insulated gate bipolar transistor (IGBT) such as those employed in photovoltaic inverters. The proposed methodology is divided into the thermo-hydraulic calculation process and the optimization of the system. This optimization is carried out using a multi-objective particle swarm optimization (PSO) algorithm that seeks the best compromise between two variables: Component temperature and manufacturing time of the impingement plate. The result is a calculation tool that can quickly find the solution that meets the requirements of the designer without the need to evaluate all possible solutions.

There is presently a need for more robust navigation algorithms for autonomous industrial vehicles. These have reasonably guaranteed the adequate reliability of the navigation. In the current work, the stability of a modified algorithm for collision-free guiding of this type of vehicle is ensured. A lateral control and a longitudinal control are implemented. To demonstrate their viability, a stability analysis employing the Lyapunov method is carried out. In addition, this mathematical analysis enables the constants of the designed algorithm to be determined. In conjunction with the navigation algorithm, the present work satisfactorily solves the localization problem, also known as simultaneous localization and mapping (SLAM). Simultaneously, a convolutional neural network is managed, which is used to calculate the trajectory to be followed by the AGV, by implementing the artificial vision. The use of neural networks for image processing is considered to constitute the most robust and flexible method for realising a navigation algorithm. In this way, the autonomous vehicle is provided with considerable autonomy. It can be regarded that the designed algorithm is adequate, being able to trace any type of path.

Artificial Neural Networks (ANNs) have proven to be a powerful tool in many fields of knowledge. At the same time, evolutionary algorithms show a very efficient technique in optimization tasks. Historically, ANNs are used in the training process of supervising networks by decreasing the error between the output and the target. However, we propose another approach in order to improve these two techniques together. The ANN is trained with the points obtained during an optimization process by a genetic algorithm and a flower pollination algorithm. The performance of this ANN is used as a stop criterion for the optimization process. This new configuration aims to reduce the number of iterations executed by the genetic optimizer when learning the cost function by an ANN. As a first step, this approach is tested with eight benchmark functions. As a second step, the authors apply it to an air jet impingement design process, optimizing the surface temperature and the fan efficiency. Finally, a comparison between the results of a regular optimization and the results obtained in the present study is presented.

The Deep Deterministic Policy Gradient (DDPG) algorithm is a reinforcement learning algorithm that combines Q-learning with a policy. Nevertheless, this algorithm generates failures that are not well understood. Rather than looking for those errors, this study presents a way to evaluate the suitability of the results obtained. Using the purpose of autonomous vehicle navigation, the DDPG algorithm is applied, obtaining an agent capable of generating trajectories. This agent is evaluated in terms of stability through the Lyapunov function, verifying if the proposed navigation objectives are achieved. The reward function of the DDPG is used because it is unknown if the neural networks of the actor and the critic are correctly trained. Two agents are obtained, and a comparison is performed between them in terms of stability, demonstrating that the Lyapunov function can be used as an evaluation method for agents obtained by the DDPG algorithm. Verifying the stability at a fixed future horizon, it is possible to determine whether the obtained agent is valid and can be used as a vehicle controller, so a task-satisfaction assessment can be performed. Furthermore, the proposed analysis is an indication of which parts of the navigation area are insufficient in training terms.