Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551014
Pertenecen a esta colección Tesis y Trabajos de grado de los Doctorados correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Reinforcement learning for controlling continuous systems with uncertain dynamics and restricted states using robust neural dynamic programming(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025-06) Guarneros Sandoval, Israel Alejandro; Chairez Oria, Jorge Isaac; emimmayorquin; Fuentes Aguilar, Rita Quetziquel; Carlos Renato Vázquez Topete; Roman Flores, Armando; Escuela de Ingeniería y Ciencias; Campus Monterrey; Ballesteros Escamilla, Mariana FelisaThis dissertation presents a comprehensive investigation into the use of advanced neural network architectures and control methodologies for modelling and controlling complex robotic systems, with a primary focus on the Stewart Gough platform. Central to this work is developing and validating novel Differential Neural Networks (DNN) architectures designed to improve the fidelity of system identification in scenarios characterized by non-linear and time-varying dynamics. Through simulation and experimental validation, a new State-Input DNN (SIADNN) demonstrated superior identification accuracy over traditional DNN, particularly in capturing dynamic behaviours where system states non-trivially influence system responses. Beyond identification, the SIADNN architecture proves to be well-suited for applications in model predictive control and adaptive control frameworks, eliminating the need for extensive linearization and reducing computational burden. Its capability to model systems with time-varying parameters enables more robust and scalable solutions in control design. Additionally, the dissertation explores integrating the DNN model into reinforcement learning (RL) pipelines, leveraging the MATLAB Reinforcement Learning Toolbox to optimize control strategies. Experimental results confirm the efficacy of this hybrid approach in enhancing trajectory tracking and overall control performance of the Stewart platform. The synergy between neural identification and learning-based control highlighted in this work offers a robust framework for dealing with uncertain, high-dimensional robotic systems. The findings advocate for the broader adoption of hybrid neural architectures in intelligent control applications and pave the way for future research in real-time adaptive and data-driven control strategies.
- Design of an interference mitigation platform for roundabout vehicular ad-hoc networks: a smart signal processing and control learning approach(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024) Ornelas Gutiérrez, Angel; Vargas Rosales, César; emimmayorquin; Zúñiga Mejía, Jaime; Zareei, Mahdi; Rodríguez Cruz, José Ramón; Escuela de Ingeniería y Ciencias; Campus Monterrey; Villalpando Hernández, RafaelaThe vehicular Ad-hoc Network (VANET) paradigm is integral to contemporary transportation systems, enabling the Internet of Vehicles (IoV) and Intelligent Transportation Systems (ITS). This research aims to deepen the knowledge of vehicular wireless communication by investigating the influence of smart signal processing and control learning strategies on interference mitigation by the Signal-to-Interference-plus-Noise Ratio (SINR) and outage performance in VANETs. Initially, the study sought to identify the best digital beamforming techniques to reduce co-channel interference and enhance communication reliability in VANET settings. Following this, it examines the incorporation of control mechanisms such as Proportional-Integral-Derivative (PID) controllers and Reinforcement Learning (RL) algorithms into VANET simulations for dynamic SINR management. Finally, the research investigates the relative efficiency of different control strategies and digital beamforming methods in reducing interference and improving communication reliability under fair conditions on a simulated roundabout VANET platform with different scenarios. Through rigorous experiments and assessments in the simulated roundabout VANET environment, the objective is to confirm the effectiveness of the suggested interference mitigation methods and offer valuable perspectives for future studies and practical implementation in real-world contexts taking advantage of the rise of cellular technologies such as 5G and 6G to advance in the development of vehicular networks with intelligent interference mitigation and SINR management framework for smart cities.
- A safe and efficient path planning framework for conformal fused filament fabrication using a manipulator arm(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-12-02) Rodríguez Padilla, Ma. Consuelo; ROMAN FLORES, ARMANDO; 46077; Román Flores, Armando; puemcuervo, emipsanchez; Cuan Urquizo, Enrique; González Hernández, Hugo Gustavo; Ramírez Cedillo, Erick Guadalupe; School of Engineering and Sciences; Campus Monterrey; Vázquez Hurtado, CarlosAs opposed to flat or planar extrusion additive manufacturing, the benefits of multi-plane and curved fused deposition of material are conclusive; however, several issues need to be considered and solved when a robotic manipulator is used for the deposition of material. The path and motion planning for printing using robotics need considerations to guarantee adequate results. This work presents the projection of a printing trajectory on a tessellated surface and a Reinforcement Learning strategy that optimizes the angular displacement of joints. The validation of the strategy is presented under simulated conditions inserting different obstacles for a projected zigzag printing pattern on a curved surface. Results show that this approach can choose the optimal inverse kinematic solution to optimize the movement of the main joints of a robot with six degrees of freedom while avoiding different obstacles. The strategy was tested on several actual printings of complex patterns on different curved surfaces using a manipulator arm UR3. Even thought the applicability of lattice manufacturing suggested here, the framework developed and software implemented and validated may be used for any application where a very precise conformal trajectory needs to be followed using a manipulator arm or any multi-axis system saving programming time.