Posts on Everardo Shain

Next Best View | Master's Thesis

Tue, 03 Dec 2024 08:06:25 +0600

Overview

This study was made with the purpose of understanding the impact of the objective function and optimization methods on the Next Best View problem, which consists in finding the next position that the sensor or camera needs to take to scan an object or scenery in its totality.

A simulated 5-Degree-of-Freedom mobile robot with a mounted simulated range sensor was used on a Virtual Reality Modeling Language environment, and the space discretization was made using a voxel map. For the objective function, two main factors were included: an area factor to make sure that the image taken by the sensor provides the best possible information, and a motion factor made up of distance and energy sub-factors to reduce the resources used by the robot, making multiple experiments on a laboratory scene to determine their best arrangement on the final objective function. Global optimization tasks such as a backstepping technique to escape local minima and a dynamic change in the objective function were implemented. The retrievement of the scene was made on an iterative process, with each iteration needing an optimization process for which three different methods were tested: Nelder-Mead, an Evolution Strategy, and Simulated Annealing.

Poker Simulation

Tue, 13 Aug 2024 08:06:25 +0600

Overview

This project was part of the Introductory C Programming specialization from Coursera, and it was developed through the entire duration of the different courses divided into smaller sections. All the code was written in C language, with the use of advanced concepts such as arrays, pointers, debugging and memory allocation.

The main task was to develop a functional poker simulator, starting with a correct card representation, building decks, implementing an extensive hand evaluation function to end with a Monte Carlo simulation system with 10000 trials for evaluating hand probabilities.

US Children Adoption Statistical Inference

Thu, 23 Nov 2023 08:06:25 +0600

Overview

Project focused on understanding behaviors on the United States children adoption using a dataset from Centers for Disease Control and Prevention, where a total of 3 hypotheses were tested using R on RStudio. My team and I performed some data cleaning to avoid missing values and separate our variables of interest to them visualize them with bar plots and pie charts. For all the hypotheses we identified the Independent 2-group Mann-Whitney U Test as the best choice and performed it, then we reinforced our analysis by applying a parametric bootstrapping and power calculation where all 3 hypotheses got a good power greater than 80%.

Industrial AGV

Mon, 05 Dec 2022 08:06:25 +0600

Overview

This was a team project in which we upgraded an existing Ackerman vehicle by turning it into an Automated Guided Vehicle. This was achieved by using ROS as framework on a NVIDIA Jetson Xavier computer and with the implementation of navigation concepts such as mapping, path planning and motion control. As a result, we managed to navigate the AGV inside a closed environment by setting a goal position and avoiding collisions.

IMDB Sentiment Analysis

Fri, 03 Jun 2022 08:06:25 +0600

Overview

This was a group project focused on the development of a sentiment analysis pipeline for IMDB movie reviews using deep learning–based natural language processing techniques. A Convolutional Neural Network (CNN) was trained to classify reviews as positive or negative, while also generating fixed-length semantic embeddings. It included dataset preprocessing, model training with pretrained word embeddings, and an inference pipeline capable of exporting 300-dimensional feature vectors from raw text inputs.

Upright CNC Router

Wed, 11 May 2022 08:06:25 +0600

Overview

This team project included the CAD modeling of a motor driven Upright CNC Router with polar axes, and its control with PD and PID controllers using MATLAB and Simulink. We designed a HMI with a mode selector menu (1 coordinate, circle, rectangle, triangle and 3 coordinates), and plotted each comparison between reference and control signals, plus an additional plot with the error signal. The most complex tasks were the signal generation for each shape by applying horizontal and vertical forces, and an additional conversion to those signals as our robot moved within polar axes. The PD and PID tuning was made by making several trial and error experiments on each mode until the stationary error was almost zero.

Robofest 2022 | Robociety

Sat, 26 Mar 2022 08:06:25 +0600

Overview

This project was a Sumo robot for the international competition Robofest 2022, fulfilling the task of pushing three bottles without falling off the table, plus an unknown initial task to be coded during the competition itself. Although my main responsibility was software development, I also contributed to the robot’s design to ensure it met the competition’s weight and size requirements.

This was part of my two-year participation as a member of Robociety, a robotics student association. Through this project, I not only developed hard skills in robot design and programming but also soft skills by mentoring new members.

Tomato Harvesting Robot

Wed, 16 Feb 2022 08:06:25 +0600

Overview

Project in collaboration with Mondragon Unibertsitatea, Tecnológico de Monterrey campuses Puebla and Queretaro. My team and I worked on the End-Effector Subsystem where we designed and built a 3D-printed prototype of a robot gripper capable of collecting tomatoes using as sensors and actuators a limit switch, a potentiometer and a stepper motor. I had the specific task of writing the code of the embedded system that controlled its movement using an Arduino UNO, and we also programmed an UR10e industrial robot to follow a certain trajectory, mounted the gripper and tested the whole system which successfully completed the tasks of collecting a tomato and placing it on a container.

Elevator

Thu, 18 Nov 2021 08:06:25 +0600

Overview

This project involves programming a simulated 4-floor elevator on a PLC using TIA Portal. Most of the code is written in SCL, with less than 30% implemented in ladder logic. The simulation replicates real-world elevator functionality and meets all 11 requirements defined in the project guidelines, including the development of a fully functional HMI.

Peer-review meetings with the project supervisor and exhaustive research were conducted on the proper functioning of real-world elevators, as some corner cases were not defined in the project requirements.

IoT Sensor Data Classification

Fri, 29 Oct 2021 08:06:25 +0600

Overview

This was an IoT project in which I implemented two machine learning algorithms, K-Nearest Neighbors (KNN) and Decision Tree, in Python to classify data collected from an MMA7361 accelerometer and a DHT11 temperature/humidity sensor connected to a NodeMCU ESP32 microcontroller. The sensors were programmed and tested using Arduino IDE, with data transmitted both through wired serial communication and wirelessly via MQTT using Mosquitto and OpenSSL for secure transfer. I organized the workflow on Jupyter Notebook, where I processed the collected data, labeled different scenarios (dark room, sunny room, bathroom, sensor movement types), and split it into training and testing sets. Both algorithms achieved good results, with accuracies above 97%, including perfect classification with the Decision Tree on the accelerometer dataset.