Ciencias Exactas y Ciencias de la Salud

Now showing 1 - 3 of 3

Analyzing VR and AR I4.0 technologies for industrial applications: A comparative study and selection approach development
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12-11) Chavez Najera, Daniela Monserrat; Ahuett Garza, Horacio; emipsanchez; Urbina Coronado, Pedro Daniel; Orta Castañón, Pedro Antonio; School of Engineering and Sciences; Campus Monterrey
In recent years, the implementation of immersive technologies such as Virtual Reality (VR) and Augmented Reality (AR) for Industry 4.0 (I4.0) applications has increased considerably. These technologies enable the connection of virtual and real environments focusing on human centered manufacturing. A challenge when implementing immersive technologies in industrial tasks is the lack of clear paths to select the most appropriate technology for specific operations, and the nonexistence of metrics to evaluate the integration performance. Nonetheless, there are trends in the literature that offer insights to conduct the decision making process for selection between immersive technologies, ensuring the suitability of the application. Based on the decision criteria identified in the literature a decision making approach is developed. This thesis also presents the development workflow of three VR/AR applications implemented in Unity Engine for Meta Quest 3 and Hololens 2. These applications are evaluated using overall performance metrics and are analyzed using the proposed approach.
Development of a 3-DOF exoskeleton for rehabilitation and training of human wrist in combination with a virtual interface
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-07-31) García Leal, Roderico Alfredo; Huegel West, Joel Carlos; puemcuervo, emipsanchez; O'Malley, Marcia K; Cruz Ortiz, David; Salgado Ramos, Iván de Jesús; González de Alba, Alejandro; School of Engineering and Sciences; Campus Monterrey; Ballesteros Escamilla, Mariana Felisa
Rehabilitation therapies produce positive outcomes by recovering the lost brain plasticity after a cerebrovascular accident or stroke; such therapies can be applied by physiotherapists with the assistance of rehabilitation devices; among these devices, robots have shown the capability of providing consistent and measurable routines for long periods. In the physiotherapy process, the upper limbs are the first parts of the body to receive rehabilitation by playing a key role in performing activities of daily living (ADL) again. In that sense, wrist rehabilitation robots are the most common device with that purpose. The thesis presented herein describes the development of an exoskeleton robot for wrist rehabilitation with three degrees of freedom (DOFs). It was designed to have the capability of proving the forces and ranges of motion required to generate wrist rehabilitation routines. The device DOFs consist of three rotational joints in series, allowing the user to effectuate the natural wrist movements: pronation/supination, flexion/extension, and radial/ulnar deviation. The exoskeleton joints are actuated directly by quasi-direct drive actuators that provide sufficient torque and speed at each DOF to replicate wrist ADLs movements. Actuator's low inertia and low friction allow the joints to be back-drivable, enhancing the transparency of the device. Robust state feedback control algorithms are implemented to achieve position control and trajectory tracking at each DOF without implementing the system's mathematical model. System characterization is obtained through the frequency response and static friction tests over each joint. The effect of the robot dynamics on the user was measured by analyzing the kinematic data of healthy participants when performing wrist movements when using and not the exoskeleton, validating the transparency of the exoskeleton joints by observing smooth velocity profiles when using the device. Finally, a pilot test is performed to demonstrate the capability of interacting with a two-dimensional virtual interface (VI) through the wrist movements performed over the exoskeleton, validating the possibility of future implementation of game-based therapies to encourage participants to perform wrist movements for their rehabilitation. The obtained results provide meaningful data demonstrating the potential of the developed exoskeleton to be used as a wrist rehabilitation device.
Use of reinforcement learning to help players improve their skills in Super Smash Bros. Melee
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-11-22) Estrada Valles, Jorge Alberto; Ramírez Uresti, Jorge Adolfo; puelquio/tolmquevedo; Morales Manzanares, Eduardo; Sosa Hernández, Víctor Adrián; Medina Pérez, Miguel Ángel; Ingenieria y Ciencias; Campus Monterrey
eSports have become a huge industry in recent years which has led to more and more people being interested in competing as professional players, however not all players have the same opportunities as things like the current residence of the player are a huge factor. This is especially true for fighting games as people who live in small cities or countries usually have the problem of finding people with whom to practice and even then it may not be the best practice, so people opt to play against in-game AI which is also not good practice. Due to this problem new and more accessible ways for players to train must be created which is why a reinforcement learning solution is proposed. In this thesis, we present a solution using Proximal Policy Optimization to help people train when their best option is against the in-game AI. Furthermore, several additions, namely multiple time step actions, reward shaping, and specialized training; are suggested to optimize the created model to be used as a training partner by a human. To evaluate the effectiveness of the resulting model the game named Super Smash Bros. Melee was used to compare the improvement achieved by training against our bot and against the in-game AI. The results show that people that trained against the bot improved more than the people that trained against the AI, proving that it is a good way to help players train for eSport competitions.

Ciencias Exactas y Ciencias de la Salud

Browse

Filters

Settings

Sort By

Results per page

Search Results