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
- Monocular obstacle avoidance framework for autonomous navigation(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025-06) Abascal Molina, Andrea; Sotelo Molina, David Alejandro; emipsanchez; Muñoz Ubando, Luis Alberto; Pinto Orozco, Arturo; School of Engineering and Sciences; Campus Monterrey; Sotelo Molina, Carlos GustavoThis thesis presents a vision-based autonomous navigation framework that integrates deep learning-based monocular depth estimation with a Model Predictive Control (MPC) strategy for dynamic obstacle avoidance in indoor Unmanned Aerial Vehicles (UAVs). The proposed system addresses key challenges of operating in cluttered indoor environments where tradi- tional localization and depth sensing solutions are impractical due to hardware constraints or environmental limitations. Leveraging a fine-tuned Depth Anything V2 model, the frame- work generates dense depth maps in real time and utilizes them to construct sector-based spatial constraints within the UAV’s visual field. These constraints are incorporated into the MPC formulation to inform predictive control decisions and enable safe trajectory planning. A visual feature extraction module based on marker detection provides the reference trajec- tory for visual servoing, while the UAV continuously updates its path to avoid obstacles using dynamic depth constraints. The system was experimentally validated on a Tello quadrotor in various indoor scenarios, including static target alignment, dynamic target tracking, and ob- stacle intrusion. The results demonstrate reliable visual tracking, real-time depth estimation reaching 40 Hz via TensorRT optimization, and successful avoidance behavior under com- plex visual conditions. The contributions of this work include the design of a lightweight real-time perception-to-control pipeline, the integration of DL-based depth constraints into an MPC framework, and the demonstration of safe, closed-loop UAV navigation in dynamic environments. Although the system is designed for aerial robots, its modular architecture and sensor-driven control strategy generalize to other mobile robotic platforms. Ultimately, this framework equips mobile robots with advanced perception capabilities that are essential for achieving higher levels of autonomy in complex and unstructured environments.
- Optimizing Route Planning in Diverse Landscapes: Integrating SLAM and RRT in Autonomous Drone Deployment.(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-06-11) Colín García, Daniel; Izquierdo Reyes, Javier; emimmayorquin; González Hernández, Hugo Gustavo; Molina Espinosa, José Martín; School of Engineering and Sciences; Campus Ciudad de MéxicoThis thesis focuses on the implementation of improved route planning and terrain mapping in different types of structured landscapes by using advanced Simultaneous Localization and Mapping (SLAM) methods and Rapidly-exploring Random Tree (RRT*) algorithm in autonomous drone deployment, focusing on software development and simulation to improve tracking capabilities. This thesis is based on a single project that is a collaborative work of postgraduate students. The project aims to develop a drone-based telecommunications network that serves as a basis for exploration and monitoring in studied or designated areas. This research is based on the establishment of a system that integrates SLAM, which provides a quick and accurate map of complex environments. This is important for the correct drones' work and the best results. Meanwhile, the inclusion of an RRT algorithm enables us to raise the system's efficiency and accuracy in planning routes for drones as they navigate intricate urban and non-urban spaces. The project is exclusively based on software simulation, using tools like AirSim and Unreal Engine, which allow the creation of an environment to test how well different drones work, from a single area to specific coordinates, ignoring external conditions like weather and drone battery life. The use of these mapping techniques and this trajectory planning algorithm enables safe navigation and an understanding of the environment that allows drones to function properly to perform their tasks. The results obtained, and the methods applied in the thesis, hope to introduce efficiency and productivity in the planning of drone deployments in all structured environments. This path would open the way to new applications in areas beyond urban infrastructure.
- Observer-based controller for unmanned aerial vehicles in reforestation applications(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-05-28) Muñoz Sepúlveda, Gustavo Alberto; Lozoya, Rafael Camilo; emimmayorquin; Castañeda, Herman; School of Engineering and Sciences; Campus Monterrey; Abaunza, HernánThis study presents a breakthrough in unmanned aerial vehicle (UAV) technology, showcas- ing the efficacy of a custom-designed controller and observer in the context of reforestation initiatives. Through meticulous experimentation and analysis, the study demonstrates the ob- server’s adeptness in mitigating external disturbances, thereby enhancing the precision and stability of UAV operations. This technological advancement not only holds promise for diverse practical applications but also holds profound implications for environmental con- servation efforts, particularly reforestation. Reforestation plays a pivotal role in mitigating climate change, preserving biodiversity, and safeguarding ecosystems. By leveraging UAV technology, this study propels forward the efficacy and efficiency of reforestation endeavors, laying the groundwork for future innovations in UAV-based interventions. The findings affirm the viability of the proposed controller and observer framework, highlighting its potential to revolutionize environmental monitoring, conservation, and sustainable resource management practices. This abstract encapsulates the significance of integrating cutting-edge technology with environmental conservation efforts, underscoring the pivotal role of UAVs in fostering a more sustainable future.
- Mobile coverage solutions for not-spots in rural zones of Latin America(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06) Cabrera Castellanos, Diego Fernando; Aragon Zavala, Alejandro; dnbsmr; Castañon Avila, Gerardo; Guerrero Gonzalez, Neil; School of Engineering and Sciences; Campus MonterreyAccess to broadband communications in different parts of the world has become a priority for some governments and regulatory authorities around the world in recent years. Building new digital roads and pursuing a connected society includes looking for easier access to the Internet. In general, not all the areas where people congregate are fully covered, especially in rural zones, thus restricting the access to data communications and therefore bringing inequality. In rural areas, there are multiple challenges to deliver reliable communication, such as a suitable roll-out of IoT structures and introducing the ubiquitous network model in the countryside. Accordingly, the use of three platforms to deliver broadband services to such remote and low-income areas were studied: Unmanned Aerial Vehicles (UAV), Altitude Platforms (APS), and Low-Earth Orbit (LEO) satellites. On the other hand, the use of terrestrial networks— such as optical fiber centered—seems suitable but non-affordable because of the rural orography’s high complexity. The analysis of terrestrials deployments is out of the proposal scope. Hence UAVs were considered a noteworthy solution to be assessed in the experimental stage—by using the algorithm performed through electronic processors—since its efficient maneuverability can encompass the rural coverage issues of not-spots. To support the primary aim of analyzing the viability of deploying alternative BSs based on UAVs, the obtained results indicated that there are manifold shortcomings in the stated model due to the limitations on the accuracy of the used devices besides the bounded number collected information. Nevertheless, this approach can become an outstanding opportunity to develop the AGC research by considering higher-level simulations and even trustworthy LTE deployments to spur a fully connected countryside in Latin America and the entire world.