André Dias

Abstract
The knowledge of the precise 3D position of a target in tracking applications is a fundamental requirement. The lack of a low-cost single sensor capable of providing the three-dimensional position (of a target) makes it necessary to use complementary sensors together. This research presents a Local Positioning System (LPS) for outdoor scenarios, based on a data fusion approach for unmodified UAV tracking, combining a vision sensor and mmWave radar. The proposed solution takes advantage of the radar's depth observation ability and the potential of a neural network for image processing. We have evaluated five data association approaches for radar data cluttered to get a reliable set of radar observations. The results demonstrated that the estimated target position is close to an exogenous ground truth obtained from a Visual Inertial Odometry (VIO) algorithm executed onboard the target UAV. Moreover, the developed system's architecture is prepared to be scalable, allowing the addition of other observation stations. It will increase the accuracy of the estimation and extend the actuation area. To the best of our knowledge, this is the first work that uses a mmWave radar combined with a camera and a machine learning algorithm to track a UAV in an outdoor scenario.

Abstract
There is a strong need to motivate students to learn science, technology, engineering, and mathematics (STEM) subjects. This is a problem not only at lower educational levels, but also at college institutions. With this idea in mind, the School of Engineering of the Porto Polytechnic (ISEP) Electrical Engineering Department decided, in 2021, to launch a robotics competition in order to foster students' interest in the areas of robotics and automation. This event, named Robotics@ISEP Open, aims to raise awareness of the area of electronics, computing, and robotics among students, involving them in the use of techniques and tools in this area, and encompasses three distinct robotics competitions covering both manipulator arms and mobile robots. It is based on two main points of interest: (i) robotic competitions and (ii) outside class training in robotics, aimed at students who want support to participate in competitions. Since its first edition, the event has grown and internationalized and has already become a milestone in the academic life of ISEP. This paper presents the motivations that led to the creation of this event, its main organizational aspects, and the competitions that are part of it, as well as some results gathered from the experience accumulated in organizing it.

Abstract
Climate change has led to the need to transition to clean technologies, which depend on an number of critical metals. These metals, such as nickel, lithium, and manganese, are essential for developing batteries. However, the scarcity of these elements and the risks of disruptions to their supply chain have increased interest in exploiting resources on the deep seabed, particularly polymetallic nodules. As the identification of these nodules must be efficient to minimize disturbance to the marine ecosystem, deep learning techniques have emerged as a potential solution. Traditional deep learning methods are based on the use of convolutional layers to extract features, while recent architectures, such as transformer-based architectures, use self-attention mechanisms to obtain global context. This paper evaluates the performance of representative models from both categories across three tasks: detection, object segmentation, and semantic segmentation. The initial results suggest that transformer-based methods perform better in most evaluation metrics, but at the cost of higher computational resources. Furthermore, recent versions of You Only Look Once (YOLO) have obtained competitive results in terms of mean average precision.

Abstract
This paper presents the Unmanned Aerial Vehicle (UAV) MANTIS, developed for indoor inventory management in large-scale warehouses. MANTIS integrates a visual odometry (VIO) system for precise localization, thus allowing indoor navigation in complex environments. The mechanical design was optimized for stability and maneuverability in confined spaces, incorporating a lightweight frame and efficient propulsion system. The UAV is equipped with an array of sensors, including a 2D LiDAR, six cameras, and two IMUs, which ensures accurate data collection. The VIO system integrates visual data with inertial measurements to maintain robust, drift-free localization. A behavior tree (BT) framework is responsible for the UAV mission planner assigned to the vehicle, which can be flexible and adaptive in response to dynamic warehouse conditions. To validate the accuracy and reliability of the VIO system, we conducted a series of tests using an OptiTrack motion capture system as a ground truth reference. Comparative analysis between the VIO and OptiTrack data demonstrates the efficacy of the VIO system in maintaining accurate localization. The results prove MANTIS, with the required payload sensors, is a viable solution for efficient and autonomous inventory management.

Abstract
Unmanned Aerial Vehicle (UAV) applications, particularly for indoor tasks such as inventory management, infrastructure inspection, and emergency response, are becoming increasingly complex with dynamic environments and their different elements. During operation, the vehicle's response depends on various decisions regarding its surroundings and the task goal. Reinforcement Learning techniques can solve this decision problem by helping build more reactive, adaptive, and efficient navigation operations. This paper presents a framework to simulate the navigation of a UAV in an operational environment, training and testing it with reinforcement learning models for further deployment in the real drone. With the support of the 3D simulator Gazebo and the framework Robot Operating System (ROS), we developed a training environment conceivably simple and fast or more complex and dynamic, explicit as the real-world scenario. The multi-environment simulation runs in parallel with the Deep Reinforcement Learning (DRL) algorithm to provide feedback for the training. TD3, DDPG, PPO, and PPO+LSTM were trained to validate the framework training, testing, and deployment in an indoor scenario.