Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Implementation of a Long Short-Term Memory neural network-based algorithm for dynamic obstacle avoidance(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-06-10) Mulás Tejeda, Esmeralda; Gómez Espinosa, Alfonso; emimmayorquin; Cantoral Ceballos, José Antonio; School of Engineering and Sciences; Campus Querétaro; Escobedo Cabello, Jesús ArturoAutonomous mobile robots are essential to the industry, and human-robot interactions are becoming more common nowadays. These interactions require that the robots navigate scenarios with static and dynamic obstacles in a safely manner, avoiding collisions. This paper presents a physical implementation of a method for dynamic obstacle avoidance using a Long Short-Term Memory (LSTM) neural network that obtains information from the mobile robot’s LiDAR for it to be capable of navigating through scenarios with static and dynamic obstacles while avoiding collisions and reaching its goal. The model is implemented using a TurtleBot3 mobile robot within an OptiTrack Motion Capture (MoCap) system for obtaining its position at any given time. The user operates the robot through these scenarios, recording its LiDAR readings, target point, position inside the MoCap system, and its linear and angular velocities, all of which serve as the input for the LSTM network. The model is trained on data from multiple user-operated trajectories across five different scenarios, outputting the linear and angular velocities for the mobile robot. Physical experiments prove that the model is successful in allowing the mobile robot to reach the target point in each scenario while avoiding the dynamic obstacle, with a validation accuracy of 97.99%
- Design and additive manufacturing of compliant grippers: modeling and experimental characterization(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-05-13) Cano Arias, Luis Enrique; Gómez Espinosa, Alfonso; emimmayorquin; Arredondo Soto, Mauricio; Escuela de Ingeniería y Ciencias; Campus Monterrey; Cuan Urquizo, EnriqueHere the design and analytical modeling of a 2D compliant gripper are developed. For this, the formulation that describes the behavior of a Flexure-Based Compliant Parallel Mechanisms (FBCPM) is considered, as well as the integration of a blade-type flexure to complete the opening and closing motion of the compliant gripper. Due to its use in precision and fracture resistance tasks, this monolithic mechanism is being analyzed. By adapting an existing compliant gripper design, the expected displacement in the flexures is obtained and the occurrence of stressed elements is reduced, achieving separation between rigid and bending elements. The use of the Compliance Matrix Method (CMM) allows to evaluate the kinetostatic analysis that relates the input force and output displacement in our selected design. A coordinate frame is considered in each blade-type flexure to establish the connection between the fixed elements and those that will experience displacement. The results obtained analytically are validated via Finite Element Method (FEM) models and experimental approach. The displacement of the fingers in the simulation is evaluated in the plane and contrasted with the analytical prediction obtaining a 5% error using the force as a input parameter. For experimental validation, the output displacement is compared with the analytical model using displacement as input value, the behaviour of the compliant gripper is validated by all three methods (analytical, FEM and experimental) with an error rate of less than 5%. Finally, the design of Architected Fingers is evaluated qualitatively to demonstrate the grip of objects with different shapes as well as the difference in printing materials.
- Maturity recognition and fruit counting for sweet peppers in greenhouses using deep Learning neural networks(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-01-05) Viveros Escamilla, Luis David; Gómez Espinosa, Alfonso; mtyahinojosa, emipsanchez; Cantoral Ceballos, José Antonio; Escuela de Ingenieria y Ciencias; Campus Querétaro; Escobedo Cabello, Jesús ArturoThis study presents an approach to address the challenges involved in recognizing the maturity stage and counting sweet peppers of varying colors (green, yellow, orange, and red) within greenhouse environments. The methodology leverages the YOLOv5 model for real-time object detection, classification, and localization, coupled with the DeepSORT algorithm for efficient tracking. The system was successfully implemented to monitor sweet pepper production, and some challenges related to this environment, namely occlusions and the presence of leaves and branches, were effectively overcome. The algorithm was evaluated using real-world data collected in a sweet pepper greenhouse. A dataset comprising 1863 images was meticulously compiled to enhance the study, incorporating diverse sweet pepper vari eties and maturity levels. Additionally, the study emphasized the role of confidence levels in object recognition, achieving a confidence level of 0.973. Furthermore, the DeepSORT algo rithm was successfully applied for counting sweet peppers, demonstrating an accuracy level of 85.7% in two simulated environments under challenging conditions, such as varied lighting and inaccuracies in maturity level assessment.
- Inspection Operations in Fish Net Cages through a Hybrid Underwater Intervention System using Deep Learning(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-11-01) López Barajas, Salvador; Gómez Espinosa, Alfonso; emimmayorquin; Sanz Valero, Pedro José; González García, Josué; School of Engineering and Sciences; Campus Querétaro; Marín Prades, RaúlNet inspection in net cages is a daily task for divers at the fish farms. This task represents a high cost for fish farms and is a high risk activity for the divers. Net cages are basically big structures with a depth of more than 20m and around 25m diameter. The total inspection surface can be more than 1500 $m^{2}$, which means that this activity is time-consuming. Considering that divers have limited time underwater, this activity represents a significant area for improvement. Additionally, a net pen is a harsh environment with hundreds of fish swimming, fish morts and ocean currents as some of the phenomena to consider. Some works have addressed this problem using underwater robots equipped with sensors such as USBL or DVL, and applying different control theories to offer a solution to this problem. A platform for net inspection is proposed in this Thesis. This platform includes a surface vehicle, ground station and an underwater vehicle embedded with artificial intelligence and control trajectories. The underwater robot used is the BlueROV2 on its heavy configuration, some localization techniques are used to control the position of the robot such as a monocular camera at the surface vehicle using an ArUco code and object detection. Computer vision is also implemented in this work, a Convolutional Neural Network was trained in order to predict the distance between the net and the robot. Finally, some experimental results about the hole detection and position algorithm, the net distance estimation and the inspection trajectories are also presented that demonstrate the robustness, usability, and viability. The experimental validation took place in the CIRTESU tank, which has dimensions of 12x8x5 meters, at Universitat Jaume I.
- Neural network circuit implementation using operational amplifiers and digital potentiometers(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06-09) Posada Hoyos, Jacobo; GOMEZ ESPINOSA, ALFONSO; 57957; Gómez Espinosa, Alfonso; puemcuervo; Escobedo Cabello, Jesus Arturo; Domínguez Oviedo, Agustín; González García, Josué; School of Engineering and Sciences; Campus Monterrey; Valdés Aguirre, BenjamínImplementations of Artificial Neural Networks (ANN) have been advancing for almost three decades and their importance has been marked by the different methods used in their construction, their applications, and comparisons in terms of speed, costs, and performance between implementations made by software and hardware. As analog implementations of ANN have been shown to have good levels of performance, high processing speed, low power consumption, small size, and low cost, they have played an important role in the development of new designs. This work presents a proposal to design a circuit implementation of an ANN by using Operational Amplifiers (Opamps) and digital potentiometers to create a network that can be trained by using an external training system. This, based on circuit analysis and training algorithm by the back propagation (BP) approach. The proposed design will be simulated in the circuit simulator Proteus. The circuit is tested using the logical gates benchmark problem to verify its performance with the BP learning algorithm. The results of this work demonstrate that it is possible to create a neural network using analogous components. Furthermore, it shows good performance when implementing the training algorithm using digital potentiometers. As future work is expected to improve the performance of training to create a controller based on neural networks and thus, perform the control of a dynamic system.
- Trajectory planning for mobile robot in dynamic environment using LSTM neural network(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06-03) Molina Leal, Alejandra; Gómez Espinosa, Alfonso; tolmquevedo; Cuan Urquizo, Enrique; Cruz Ramírez, Sergio Rolando; Escuela de Ingeniería y Ciencias; Campus Monterrey; Escobedo Cabello, Jesús ArturoAutonomous mobile robots are an important focus of current research due to the advantages they bring to the industry, such as performing dangerous tasks with greater precision than humans. An autonomous mobile robot must be able to generate a collision-free trajectory while avoiding static and dynamic obstacles from the specified start location to the target location. Machine Learning, a sub-field of Artificial Intelligence, is applied to create a Long Short-Term Memory (LSTM) neural network that is implemented and executed to let a mobile robot find the trajectory between two points and navigate while avoiding a dynamic obstacle. The input of the network is the distance between the mobile robot and the obstacles thrown by the LiDAR sensor, the desired target location, and the mobile robot location with respect to the odometry reference frame. Using the model to learn the mapping between input and output in the sample data, the linear and angular velocity of the mobile robot are obtained. The mobile robot and its dynamic environment are simulated in Gazebo, which is an open-source 3D robotics simulator. Gazebo can be synchronized with ROS (Robot Operating System). The computational experiments show that the network model can plan a safe navigation path in a dynamic environment.
- Synthesis of a finite-time convergence controller for trajectory tracking of unmanned underwater vehicles(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06) Narcizo Nuci, Néstor Alejandro; Salgado Jiménez, Tomás; 201232; Gómez Espinosa, Alfonso; emipsanchez; Salgado Jiménez, Tomás; González García, Josué; Escuela de Ingeniería y Ciencias; Campus Monterrey; García Valdovinos, Luis GovindaUnmanned underwater vehicles have gained importance since they can perform tasks in underwater environments such as exploration and construction. Proper control of the vehicle trajectory is fundamental for successfully complete a task. When disturbances are frequent and the dynamics of the vehicle change, fast response of the control scheme is required and the classical controllers do not adapt to overcome these conditions. As the main contribution of this work, we propose the synthesis and implementation of a control scheme with finite-time convergence applied to the trajectory tracking including a time variable gain in the sliding surface of a 2nd Order Sliding Mode Control. In the first part, the parameterized trajectory considered five degrees of freedom: x,y,z, \phi, and \psi. In a second part, an emulation of a simultaneous scheme between two vehicles is proposed, taking advantage of the finite-time convergence of the proposed controller. The dynamic parameterization of the vehicle is based on the BlueROV2 vehicle by BlueRobotics, which counts with four horizontal and vectored thrusters, and two vertical thrusters. A finite-time second-order sliding-mode controller will be synthesized by applying a variable gain on the sliding surface. This gain will be parametrized by a Time Base Generator. The controller was tested to determine its performance, accuracy, and prompt response for trajectory tracking in space and was compared against classical controllers: a Proportional-Integral-Derivative Controller, a Feedback Linearization controller, and a Lyapunov function-based controller. In the second part, the controller was compared with two state-of-the-art controllers, that also count with finite-time convergence. The proposed control schemes will be evaluated in a simulator constructed in a Matlab/ Simulink environment with the actual parameters of the underwater vehicle, and where the parameters of the RMS values of the tracking error and the RMS values of the control signals are analyzed to evaluate the performance of the controllers. The results of this work demonstrated that it is possible to synthesize the 2nd Order Sliding Mode Controller with finite-time convergence and apply it in the trajectory tracking of underwater vehicles, in trajectories that involved the five degrees of freedom, and even in the presence of marine currents. The results of this thesis are expected to be implemented in future work related to trajectory tracking and collaborative tasks with underwater vehicles.
- Robotic-computer vision system for 3D welding trajectories(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06) Rodríguez Suárez, Jesús Braian; GOMEZ ESPINOSA, ALFONSO; 57957; Gómez Espinosa, Alfonso; emipsanchez; Escobedo Cabello, Jesús Arturo; Swenson Durie, Rick Leigh; Escuela de Ingeniería y Ciencias; Campus Monterrey; Cuan Urquizo, EnriqueThe necessity for intelligent welding robots that meet the demand in the real industrial production, according to the objectives of Industry 4.0, has been supported thanks to the rapid development of computer vision and the use of new technologies. In order to improve the efficiency in weld location for industrial robots, this work focuses on trajectory extraction based on color features identification over three-dimensional surfaces acquired with a depth-RGB sensor. The system is planned to be used with a low-cost Intel RealSense D435 sensor for the reconstruction of 3D models based on stereo vision and the built-in color sensor to quickly identify the objective trajectory, since the parts to be welded are previously marked with different colors, indicating the locations of the welding trajectories to be followed. This work focuses on the use of point cloud and a color data to obtain a three-dimensional model of the workpiece with which the points of the target trajectory are segmented by color thresholds in the RGB and the HSV color space, finally a spline cubic interpolation algorithm is implemented to obtain a smooth trajectory. Experimental results show that the RMSE error for V-type butt-joint path extraction is under 1.1 mm and below 0.6 mm for a straight butt joint, showing a suitable system for welding bead of various shapes and materials. It is important to note that to demonstrate its application in a robotic environment, the expected results will be presented in virtual environments created on the Robot Operating System (ROS) software.
- Sensor data fusion for a mobile robot using a neural network algorithm(Instituto Tecnológico y de Estudios Superiores de Monterrey) Barreto Cubero, Andrés Javier; GOMEZ ESPINOSA, ALFONSO; 57957; Gómez Espinosa, Alfonso; puelquio, emipsanchez; Cuan Urquizo, Enrique; Cruz Ramírez, Sergio Rolando; Escuela de Ingeniería y Ciencias; Campus Monterrey; Escobedo Cabello, Jesús ArturoMobile robots must be capable to obtain an accurate map of their surroundings and move within it. To detect different materials that might be undetectable to one sensor but not others it is necessary to have at least two sensors, with this is possible to generate a 2D occupancy map that is as close to reality as possible. In this thesis, an artificial neural network is used to fuse data from a tri-sensor (Intel RealSense Stereo Camera, 2D 360° LiDAR-Light Detection and Ranging Sensor and an HC-SR04 Ultrasonic Sensor) setup capable of detecting glass, polished metals, brick walls, wooden panels and other materials typically found in indoor environments. When a map is to be compiled out of different sensor’s data, it is necessary to implement a preprocessing scheme to filter all the outliers in the data for each sensor. Then, run a data fusion algorithm to integrate all the information into a single, more accurate 2D map that considers all sensor’s information. The Robotis Turtlebot 3 Waffle Pi robot is used as an experimental platform along with Robotic Operating System as the main Human Machine Interface to implement the algorithms. Test results show that with the fusion algorithm implemented, it is possible to detect glass and other obstacles invisible to the LiDAR with an estimated root-mean-square error of 4 cm with multiple sensor configurations.