Browsing by Author "Grilo, Vinicius F.S.B."
Now showing 1 - 6 of 6
Results Per Page
Sort Options
- Angle assessment for upper limb rehabilitation: a novel light detection and ranging (LiDAR)-based approachPublication . Klein, Luan C.; Chellal, Arezki Abderrahim; Grilo, Vinicius F.S.B.; Braun, João; Gonçalves, José; Pacheco, Maria F.; Fernandes, Florbela P.; Monteiro, Fernando C.; Lima, JoséThe accurate measurement of joint angles during patient rehabilitation is crucial for informed decision making by physiotherapists. Presently, visual inspection stands as one of the prevalent methods for angle assessment. Although it could appear the most straightforward way to assess the angles, it presents a problem related to the high susceptibility to error in the angle estimation. In light of this, this study investigates the possibility of using a new approach to angle calculation: a hybrid approach leveraging both a camera and LiDAR technology, merging image data with point cloud information. This method employs AI-driven techniques to identify the individual and their joints, utilizing the cloud-point data for angle computation. The tests, considering different exercises with different perspectives and distances, showed a slight improvement compared to using YOLO v7 for angle calculation. However, the improvement comes with higher system costs when compared with other image-based approaches due to the necessity of equipment such as LiDAR and a loss of fluidity during the exercise performance. Therefore, the cost-benefit of the proposed approach could be questionable. Nonetheless, the results hint at a promising field for further exploration and the potential viability of using the proposed methodology.
- Assessing the Reliability of AI-Based Angle Detection for Shoulder and Elbow RehabilitationPublication . Klein, Luan C.; Chellal, Arezki Abderrahim; Grilo, Vinicius F.S.B.; Gonçalves, José; Pacheco, Maria F.; Fernandes, Florbela P.; Monteiro, Fernando C.; Lima, JoséAngle assessment is crucial in rehabilitation and significantly influences physiotherapists’ decision-making. Although visual inspection is commonly used, it is known to be approximate. This work aims to be a preliminary study about using the AI image-based to assess upper limb joint angles. Two main frameworks were evaluated: MediaPipe and Yolo v7. The study was performed with 28 participants performing four upper limb movements. The results showed that Yolo v7 achieved greater estimation accuracy than Mediapipe, with MAEs of around 5◦ and 17◦, respectively. However, even with better results, Yolo v7 showed some limitations, including the point of detection in only a 2D plane, the higher computational power required to enable detection, and the difficulty of performing movements requiring more than one degree of Freedom (DOF). Nevertheless, this study highlights the detection capabilities of AI approaches, showing be a promising approach for measuring angles in rehabilitation activities, representing a cost-effective and easyto- implement solution.
- Design and Development of an Omnidirectional Mecanum Platform for the RobotAtFactory 4.0 CompetitionPublication . Braun, João; Baidi, Kaïs; Bonzatto, Luciano; Berger, Guido; Pinto, Milena F.; Kalbermatter, Rebeca B.; Klein, Luan C.; Grilo, Vinicius F.S.B.; Pereira, Ana I.; Costa, Paulo Gomes da; Lima, JoséRobotics competitions are highly strategic tools to engage and motivate students, cultivating their curiosity and enthusiasm for technology and robotics. These competitions encompass various disciplines, such as programming, electronics, control systems, and prototyping, often beginning with developing a mobile platform. This paper focuses on designing and implementing an omnidirectional mecanum platform, encompassing aspects of mechatronics, mechanics, electronics, kinematics models, and control. Additionally, a simulation model is introduced and compared with the physical robot, providing a means to validate the proposed platform.
- Development of a Low-Cost 3D Mapping Technology with 2D LIDAR for Path Planning Based on the A* AlgorithmPublication . Ferreira, Edilson Santos; Grilo, Vinicius F.S.B.; Braun, João; Santos, Murillo F. dos; Pereira, Ana I.; Costa, Paulo Gomes da; Lima, JoséThis article presents the development of a low-cost 3D mapping technology for trajectory planning using a 2D LiDAR and a stepper motor. The research covers the design and implementation of a circuit board to connect and control all components, including the LiDAR and motor. In addition, a 3D printed support structure was developed to connect the LiDAR to the motor shaft. System data acquisition and processing are addressed, as well as the generation of the point cloud and the application of the A* algorithm for trajectory planning. Experimental results demonstrate the effectiveness and feasibility of the proposed technology for low-cost 3D mapping and trajectory planning applications.
- Impact of EMG Signal Filters on Machine Learning Model Training: A Comparison with Clustering on Raw SignalPublication . Barbosa, Ana Carolina; Ferreira, Edilson Santos; Grilo, Vinicius F.S.B.; Mattos, Laercio; Lima, JoséOur current society faces challenges in integrating individuals with disabilities, making this process difficult and painful. People with disabilities (PwD) are often mistakenly considered incapable due to the difficulties they face in daily tasks due to the lack of adapted means and tools. In this context, assistive technologies play a crucial role in improving the quality of life for these individuals. However, assistive technologies still have various limitations, making research in this area essential to enhance existing solutions and develop new approaches that meet individual needs, aiming to promote inclusion and equal opportunities. This paper presents a research project that focuses on the study of electromyography (EMG) signal processing generated by individuals who have undergone amputations. These signals are essential in assistive technologies, such as myoelectric prostheses. The study focuses on the impact of different filters and machine learning training methods on this processing. The results of this study have the potential to provide relevant findings for the development of more efficient assistive technologies. By understanding the processing of EMG signals and applying machine learning techniques, it is possible to improve the accuracy and response speed of prosthetics, increasing the functionality and naturalness of movements performed by users, as well as paving the way for the emergence of new technologies.
- Retrofitting industrial robotics: an embedded system approach to controller enhancementPublication . Grilo, Vinicius F.S.B.; Lima, José; Chaves, Fabiano DrumondThe increase in productivity and efficiency caused by the presence of robots in industries and in automation processes, whether they are mobile robots or manipulator robots, encourages research and makes the area of robotics widely studied in academic scope around the world. The development methodology began with a study of the functioning of the internal modules of the original FANUC RJ Controller model, including the main controllers, circuits responsible for driving the motors and emergency systems, in order to assess which modules could be reused in the new architecture proposed for the controller. As a result, in addition to the robot’s mechanical unit, the FANUC Servo Amplifiers, the EMG Board, the Power Supply Unit, the Dynamic Brake Unit and the Main AC Power Distribution were reused in the development of the proposed controller, and a detailed study of these components was carried out. The proposed controller architecture includes the modularization of the motor position controllers, where the Dual Axis Control Board was developed, a system capable of controlling two PMSM motors via the FANUC Servo Amplifier, requiring three groups of these systems to control the robot’s six motors. To calculate the kinematics and trajectory, an ESP32-S3 was used, which receives the user’s commands, calculates the trajectory and angles of each joint of the robot and sends the angular references so that the motor controllers can act to move the robot. To integrate the systems, the Main Board Controller was developed, responsible for ensuring communication between the ESP32-S3 and the Dual Axis Control Boards, as well as providing auxiliary circuits for the emergency signals sent and received from the EMG Board. In order to improve interaction with the user and visualization of the trajectories executed by the robot, a graphical interface was developed capable of receiving positioning com- mands from the user using its own programming language and displaying the robot’s positioning using a 3D model of the FANUC S-420FD developed and incorporated into the system. Tests and validations carried out with the circuits developed showed that the signal processing and conditioning achieved the expected results, proving that the PCBs work. The algorithms developed to perform the kinematics and trajectory calcula- tions were also validated, with high accuracy and processing times in line with the rest of the system. It can therefore be concluded that the results presented make it possible to achieve the objectives initially proposed.