Abstract
Reinforcement Learning (RL) is a well-suited paradigm to train robots since it does not require any previous information or database to train an agent. This paper explores using Deep Reinforcement Learning (DRL) to train a robot to navigate in maps containing different sorts of obstacles and which emulate hallways. Training and testing were performed using the Flatland 2D simulator and a Deep Q-Network (DQN) provided by OpenAI gym. Different sets of maps were used for training and testing. The experiments illustrate how well the robot is able to navigate in maps distinct from the ones used for training by learning new behaviours (namely following walls) and highlight the key challenges when solving this task using DRL, including the appropriate definition of the state space and reward function, as well as of the stopping criteria during training.

Abstract
Selective thinning is a crucial operation to reduce forest ignitable material, to control the eucalyptus species and maximise its profitability. The selection and removal of less vigorous stems allows the remaining stems to grow healthier and without competition for water, sunlight and nutrients. This operation is traditionally performed by a human operator and is time-intensive. This work simplifies selective thinning by removing the stem selection part from the human operator's side using a computer vision algorithm. For this, two distinct datasets of eucalyptus stems (with and without foliage) were built and manually annotated, and three Deep Learning object detectors (YOLOv5, YOLOv7 and YOLOv8) were tested on real context images to perform instance segmentation. YOLOv8 was the best at this task, achieving an Average Precision of 74% and 66% on non-leafy and leafy test datasets, respectively. A computer vision algorithm for automatic stem selection was developed based on the YOLOv8 segmentation output. The algorithm managed to get a Precision above 97% and a 81% Recall. The findings of this work can have a positive impact in future developments for automatising selective thinning in forested contexts.

Abstract
Directed Energy Deposition (DED) is crucial in additive manufacturing for various industries like aerospace, automotive, and biomedical. Precise temperature control is essential due to high-power lasers and dynamic environmental changes. Employing Reinforcement Learning (RL) can help with temperature control, but challenges arise from standardization and sample efficiency. In this study, a model-based Reinforcement Learning (MBRL) approach is used to train a DED model, improving control and efficiency. Computational models evaluate melt pool geometry and temporal characteristics during the process. The study employs the Allen-Cahn phase field (AC-PF) model using the Finite Element Method (FEM) with the Multi-physics Object-Oriented Simulation Environment (MOOSE). MBRL, specifically Dyna-Q+, outperforms traditional Q-learning, requiring fewer samples. Insights from this research aid in advancing RL techniques for laser metal additive manufacturing.

Abstract
Simulators have been increasingly used on development and tests on several areas. They allow to speed up the development without damage and no extra costs. On realistic simulators, where kinematics play an important role, the modelling process should be imported for each component to be accurately simulated. Some robots are not yet modelled, as for example the Monera. This paper presents a model of a small vibration robot (Monera) that is acquired in a developed test-bed. A localisation ground truth is used to acquire the position of the Monera with actuating it. Linear and angular speeds acquired from real experiments allow to validate the proposed methodology.

Abstract
This survey analyses and compares ten different robots capable of hybrid locomotion in an attempt to elucidate the readers on several aspects of importance when designing and implementing a legged-wheeled vehicle. With this purpose in mind, the robots are compared based on their goals, kinematic configurations, joint specifications and overall performance. In this text, their variety and versatility is presented, justifying their use in real-world scenarios.

Abstract
Navigation is one of the most important tasks for a mobile robot and the localisation is one of its main requirements. There are several types of localisation solutions such as LiDAR, Radio-frequency and acoustic among others. The well-known line follower has been a solution used for a long time ago and still remains its application, especially in competitions for young researchers that should be captivated to the scientific and technological areas. This paper describes two methodologies to estimate the position of a robot placed on a gradient line and compares them. The Least Squares and the Machine Learning methods are used and the results applied to a real robot allow to validate the proposed approach.