Browsing by Author "Martins, Felipe N."
Now showing 1 - 7 of 7
Results Per Page
Sort Options
- Deep learning-based localization approach for autonomous robots in the robotAtFactory 4.0 competitionPublication . Klein, Luan C.; Mendes, João; Braun, João; Martins, Felipe N.; Oliveira, Andre Schneider; Costa, Paulo Gomes da; Wörtche, Heinrich; Lima, JoséAccurate localization in autonomous robots enables effective decision-making within their operating environment. Various methods have been developed to address this challenge, encompassing traditional techniques, fiducial marker utilization, and machine learning approaches. This work proposes a deep-learning solution employing Convolutional Neural Networks (CNN) to tackle the localization problem, specifically in the context of the RobotAtFactory 4.0 competition. The proposed approach leverages transfer learning from the pre-trained VGG16 model to capitalize on its existing knowledge. To validate the effectiveness of the approach, a simulated scenario was employed. The experimental results demonstrated an error within the millimeter scale and rapid response times in milliseconds. Notably, the presented approach offers several advantages, including a consistent model size regardless of the number of training images utilized and the elimination of the need to know the absolute positions of the fiducial markers.
- Deep reinforcement learning applied to a robotic pick-and-place applicationPublication . Gomes, Natanael Magno; Martins, Felipe N.; Lima, José; Wörtche, HeinrichIndustrial robot manipulators are widely used for repetitive applications that require high precision, like pick-and-place. In many cases, the movements of industrial robot manipulators are hard-coded or manually defined, and need to be adjusted if the objects being manipulated change position. To increase flexibility, an industrial robot should be able to adjust its configuration in order to grasp objects in variable/ unknown positions. This can be achieved by off-the-shelf visionbased solutions, but most require prior knowledge about each object to be manipulated. To address this issue, this work presents a ROS-based deep reinforcement learning solution to robotic grasping for a Collaborative Robot (Cobot) using a depth camera. The solution uses deep Q-learning to process the color and depth images and generate a ϵ- greedy policy used to define the robot action. The Q-values are estimated using Convolutional Neural Network (CNN) based on pre-trained models for feature extraction. Experiments were carried out in a simulated environment to compare the performance of four different pretrained CNN models (RexNext, MobileNet, MNASNet and DenseNet). Results show that the best performance in our application was reached by MobileNet, with an average of 84 % accuracy after training in simulated environment.
- Editorial: Educational robotics and competitionsPublication . Martins, Felipe N.; Lima, José; Oliveira, Andre Schneider; Costa, Paulo Gomes da; Eguchi, AmySTEM education endeavors to instill fundamental principles of science, technology, engineering, and mathematics, fostering a passion that propels students toward careers in these fields. Robotics, as a formidable educational tool, goes beyond theoretical learning by immersing students in practical projects that demand problem-solving skills. Its inherently multidisciplinary nature encourages the integration of knowledge from traditionally distinct disciplines, enriching the educational experience. In the ever-evolving landscape of STEM education, the integration of robotics has proven to be a dynamic catalyst for inspiring students and advancing research in science, technology, engineering, and mathematics. The latest strides in this interdisciplinary field are encapsulated in four articles published in the Research Topic on Educational Robotics and Competitions. These articles shed light on diverse aspects of robotics challenges, from virtual and real-world competitions to classroom applications.
- Enhancing motivation and learning in engineering courses: a challenge-based approach to teaching embedded systemsPublication . Lima, José; Pinto, Milena F.; Martins, Felipe N.; Hering-Bertram, Martin; Costa, Paulo Gomes daThis paper addresses an approach to teaching embedded systems programming through a challenge-based competition involving robots. This pedagogical project distinguishes itself by incorporating international students from three international institutions through the Blended Intensive Program (BIP). The research findings indicate that this approach yields excellent results regarding student engagement and learning outcomes. The challenge-based program effectively promotes students’ creative problem-solving abilities by combining theoretical instruction with hands-on experience in a competitive setting.
- A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competitionPublication . Klein, Luan C.; Braun, João; Mendes, João; Pinto, Vítor H.; Martins, Felipe N.; Oliveira, Andre Schneider; Oliveira, Andre Schneider; Wörtche, Heinrich; Costa, Paulo Gomes da; Lima, JoséLocalization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.
- Teaching practical robotics during the COVID-19 pandemic: a case study on regular and hardware-in-the-loop simulationsPublication . Lima, José; Martins, Felipe N.; Costa, Paulo Gomes daLaboratory experiments are important pedagogical tools in engineering courses. Restrictions related to the COVID-19 pandemic made it very difficult or impossible for laboratory classes to take place, resulting on a fast transition to simulation as an approach to guarantee the effectiveness of teaching. Simulation environments are powerful tools that can be adopted for remote classes and self-study. With these tools, students can perform experiments and, in some cases, make use of the laboratory facilities from outside of the University. This paper proposes and describes two free tools developed during the COVID-19 pandemic lock-down that allowed students to work from home, namely a set of simulation experiments and a Hardware-in-the-loop simulator, accessible 24/7. Two approaches in Python and C languages are presented, both in the context of Robotics courses for Engineering students. Successful results and student feedback indicate the effectiveness of the proposed approaches in institutions in Portugal and in the Netherlands.
- Using machine learning approaches to localization in an embedded system on RobotAtFactory 4.0 competition: a case studyPublication . Klein, Luan C.; Braun, João; Martins, Felipe N.; Wörtche, Heinrich; Oliveira, Andre Schneider; Mendes, João; Pinto, Vítor H.; Costa, Paulo Gomes daThe use of machine learning in embedded systems is an interesting topic, especially with the growth in popularity of the Internet of Things (IoT). The capacity of a system, such as a robot, to self-localize, is a fundamental skill for its navigation and decision-making processes. This work focuses on the feasibility of using machine learning in a Raspberry Pi 4 Model B, solving the localization problem using images and fiducial markers (ArUco markers) in the context of the RobotAtFactory 4.0 competition. The approaches were validated using a realistically simulated scenario. Three algorithms were tested, and all were shown to be a good solution for a limited amount of data. Results also show that when the amount of data grows, only Multi-Layer Perception (MLP) is feasible for the embedded application due to the required training time and the resulting size of the model.