Learning
A log of academic coursework and self-directed online learning.
Academic
West Virginia University
Spring 2020
Methods and applications of linear algebra across engineering and science: linear systems, matrix algebra, vector spaces, linear transformations, eigenvalues and eigenvectors, orthogonality, LU-factorization, Gram-Schmidt process, and least squares.
Principles of satellite-based navigation including GPS/GNSS signal processing, positioning algorithms, error sources, differential corrections, and applications in autonomous vehicles and robotics.
Audited MAE 413 (Robotic Manipulators). Topics included forward and inverse kinematics, workspace analysis, Jacobians, rigid-body dynamics, trajectory planning, and control of serial robot arms. Graduate level coursework developing code for NASA Space Robotics Challenge Phase 2.
Fall 2020
Special topics covering classical and sampling-based motion planning: configuration spaces, potential fields, RRT, PRM, and optimal planners including FMT* and RRT*.
Design of control systems using classical, frequency-domain, and state-space methods: modeling, compensation, stabilization, pole placement, and state estimation, with extensive use of MATLAB.
Spring 2021
Special topics on reinforcement learning for robotics: Markov decision processes, value iteration, policy iteration, Q-learning, deep reinforcement learning, and applications to robotic control.
Fall 2021
Classical numerical analysis with emphasis on theory and computation: root finding, interpolation, numerical integration, ODE solvers, and iterative linear solvers.
Spring 2022
Optimization of feedback systems: calculus of variations, Pontryagin's maximum principle, Hamilton-Jacobi-Bellman equation, dynamic programming, LQR, and adaptive feedback.
Summer 2023
Summer industry internship at L5 Automation, applying graduate-level robotics and software engineering skills in a professional setting.
Fall 2023
Self-directed study of behavior trees for autonomous agent control, following Colledanchise & Ögren's "Behavior Trees in Robotics and AI" (CRC Press, 2018). Topics: BT semantics, modularity, reactivity, safety analysis, and integration with planning and learning.
EESC-USP
2nd Sem. 2015
Sensor technologies, signal conditioning, data acquisition systems, measurement uncertainty, and calibration methods for mechanical and fluid systems.
Numerical methods for fluid flow simulation: finite difference and finite volume discretization, turbulence modeling, mesh generation, and practical use of CFD solvers.
Scientific writing, research design, and systematic literature review. Academic integrity, citation standards, and methodological frameworks for engineering research.
1st Sem. 2016
Advanced mathematical tools for engineering: ODEs and PDEs, Fourier and Laplace transforms, vector calculus, complex analysis, and applied numerical methods.
Fundamentals of fluid mechanics: continuity, momentum and energy equations, laminar and turbulent flows, boundary layers, drag and lift, and introduction to compressible flows.
Advanced aerodynamics including subsonic and transonic flow theory and vortex dynamics, plus aeroacoustic fundamentals: noise sources, Lighthill's analogy, and computational aeroacoustics.
Online Programs
Flying Car and Autonomous Flight Engineer
Udacity
End-to-end autonomous flight engineering: from quadrotor physics and 3D motion planning to nonlinear control and state estimation for real aerial vehicles.
- Introduction to Autonomous Flight Quadrotor rigid-body dynamics, hover and attitude control, and minimum-snap trajectory generation through waypoints.
- Planning 3D motion planning for UAVs: A*, probabilistic roadmaps, RRT, and receding-horizon planning in cluttered environments.
- Controls Cascaded PID and nonlinear geometric controllers for precise 3D trajectory tracking.
- Estimation Sensor fusion for state estimation: extended and unscented Kalman filters for GPS/IMU integration.
- Fixed-Wing Flight Longitudinal and lateral flight dynamics, aerodynamic modeling, and autopilot design for fixed-wing aircraft.
Robotics Specialization
University of Pennsylvania
A six-course program covering all major subsystems of a robotic platform, combining rigorous theory with MATLAB-based programming projects.
- Aerial Robotics UAV dynamics, PD trajectory-tracking controllers, and minimum-jerk path generation for quadrotors.
- Computational Motion Planning Graph-search planners (A*, Dijkstra), potential-field methods, and configuration-space planning for articulated robots.
- Mobility Legged and wheeled locomotion: gait analysis, terrain navigation, and bio-inspired mobility strategies.
- Perception Computer vision for robotics: homography, feature detection (SIFT), camera calibration, and visual tracking.
- Estimation and Learning Kalman filtering and particle filters applied to probabilistic robot localization against a known map.
- Capstone Hardware project: built a differential-drive robot running ROS that autonomously navigated a course using AprilTag visual landmarks.
Deep Learning Specialization
DeepLearning.AI
A five-course program by Andrew Ng covering the theory and practice of modern deep learning, from foundational networks to CNNs, RNNs, and transformers.
- Neural Networks and Deep Learning Foundations: logistic regression, shallow and deep networks, forward/backpropagation, and vectorized implementations in Python.
- Improving Deep Neural Networks Hyperparameter tuning, regularization (dropout, L2), batch normalization, and optimization algorithms (Adam, RMSProp).
- Structuring Machine Learning Projects ML strategy: bias-variance analysis, error analysis, transfer learning, and multi-task learning.
- Convolutional Neural Networks CNN architectures (ResNet, Inception), object detection (YOLO), face recognition, and neural style transfer.
- Sequence Models RNNs, LSTMs, GRUs, and transformer architectures for NLP: language modeling, machine translation, and NER with HuggingFace.